API tools faq
paste
Guest User

Untitled

a guest
Mar 5th, 2026
74
0
Never
8
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 46.94 KB | None | 0 0
raw download clone embed print report
  1. % ollama ps
  2. NAME ID SIZE PROCESSOR CONTEXT UNTIL
  3. qwen3.5:35b-a3b-q8_0 655d273ede3a 42 GB 100% GPU 65536 4 minutes from now
  4.  
  5. % cat server.log
  6. time=2026-03-05T06:40:36.958-05:00 level=INFO source=routes.go:1664 msg="server config" env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:65536 OLLAMA_DEBUG:DEBUG OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/Users/cgk/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD:false OLLAMA_NUM_PARALLEL:2 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]"
  7. time=2026-03-05T06:40:36.958-05:00 level=INFO source=routes.go:1666 msg="Ollama cloud disabled: false"
  8. time=2026-03-05T06:40:36.996-05:00 level=INFO source=images.go:477 msg="total blobs: 2309"
  9. time=2026-03-05T06:40:37.000-05:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0"
  10. time=2026-03-05T06:40:37.001-05:00 level=INFO source=routes.go:1719 msg="Listening on [::]:11434 (version 0.17.6)"
  11. time=2026-03-05T06:40:37.001-05:00 level=DEBUG source=sched.go:145 msg="starting llm scheduler"
  12. time=2026-03-05T06:40:37.001-05:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
  13. time=2026-03-05T06:40:37.002-05:00 level=INFO source=server.go:430 msg="starting runner" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --port 64200"
  14. time=2026-03-05T06:40:37.002-05:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_NO_CLOUD=0 OLLAMA_MODELS=/Users/cgk/.ollama/models OLLAMA_DEBUG=1 OLLAMA_FLASH_ATTENTION=1 PATH="/Users/CGK/qt/6.10.1/macos/bin:/Users/cgk/.pyenv/shims:/opt/homebrew/bin:/opt/homebrew/sbin:/usr/local/bin:/System/Cryptexes/App/usr/bin:/usr/bin:/bin:/usr/sbin:/sbin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/local/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/appleinternal/bin:/opt/pmk/env/global/bin:/Library/Apple/usr/bin:/Applications/VMware Fusion.app/Contents/Public" OLLAMA_MAX_LOADED_MODELS=1 OLLAMA_NEW_ESTIMATES=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_CONTEXT_LENGTH=65536 OLLAMA_HOST=0.0.0.0 DYLD_LIBRARY_PATH=/Applications/Ollama.app/Contents/Resources OLLAMA_LIBRARY_PATH=/Applications/Ollama.app/Contents/Resources
  15. time=2026-03-05T06:40:37.098-05:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=96.864875ms OLLAMA_LIBRARY_PATH=[/Applications/Ollama.app/Contents/Resources] extra_envs=map[]
  16. time=2026-03-05T06:40:37.098-05:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=1
  17. time=2026-03-05T06:40:37.098-05:00 level=DEBUG source=runner.go:193 msg="adjusting filtering IDs" FilterID=0 new_ID=0
  18. time=2026-03-05T06:40:37.098-05:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=97.034667ms
  19. time=2026-03-05T06:40:37.098-05:00 level=INFO source=types.go:42 msg="inference compute" id=0 filter_id=0 library=Metal compute=0.0 name=Metal description="Apple M3 Max" libdirs="" driver=0.0 pci_id="" type=discrete total="58.0 GiB" available="58.0 GiB"
  20. time=2026-03-05T06:40:37.098-05:00 level=INFO source=routes.go:1769 msg="vram-based default context" total_vram="58.0 GiB" default_num_ctx=262144
  21. [GIN] 2026/03/05 - 06:40:37 | 200 | 33.375µs | 127.0.0.1 | GET "/api/version"
  22. [GIN] 2026/03/05 - 06:40:37 | 200 | 84.583µs | 127.0.0.1 | HEAD "/"
  23. time=2026-03-05T06:40:37.509-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
  24. [GIN] 2026/03/05 - 06:40:37 | 200 | 158.033792ms | 127.0.0.1 | POST "/api/show"
  25. time=2026-03-05T06:40:37.632-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
  26. [GIN] 2026/03/05 - 06:40:37 | 200 | 113.353ms | 127.0.0.1 | POST "/api/show"
  27. time=2026-03-05T06:40:37.771-05:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=1µs
  28. time=2026-03-05T06:40:37.787-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
  29. time=2026-03-05T06:40:37.788-05:00 level=DEBUG source=sched.go:256 msg="loading first model" model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0
  30. time=2026-03-05T06:40:37.818-05:00 level=WARN source=sched.go:450 msg="model architecture does not currently support parallel requests" architecture=qwen35moe
  31. time=2026-03-05T06:40:37.842-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
  32. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.pooling_type default=0
  33. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.attention.head_count_kv default=0
  34. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.scaling.type default=""
  35. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.type default=""
  36. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.scaling.factor default=1
  37. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.scaling.original_context_length default=0
  38. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.attention.scale default=0
  39. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.norm_top_k_prob default=true
  40. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.mrope_interleaved default=false
  41. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.vision.attention.layer_norm_epsilon default=9.999999974752427e-07
  42. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.vision.rope.freq_base default=10000
  43. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.vision.num_positional_embeddings default=2304
  44. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false
  45. time=2026-03-05T06:40:37.844-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
  46. time=2026-03-05T06:40:37.844-05:00 level=INFO source=server.go:246 msg="enabling flash attention"
  47. time=2026-03-05T06:40:37.845-05:00 level=INFO source=server.go:430 msg="starting runner" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 --port 64206"
  48. time=2026-03-05T06:40:37.845-05:00 level=DEBUG source=server.go:431 msg=subprocess OLLAMA_NO_CLOUD=0 OLLAMA_MODELS=/Users/cgk/.ollama/models OLLAMA_DEBUG=1 OLLAMA_FLASH_ATTENTION=1 PATH="/Users/CGK/qt/6.10.1/macos/bin:/Users/cgk/.pyenv/shims:/opt/homebrew/bin:/opt/homebrew/sbin:/usr/local/bin:/System/Cryptexes/App/usr/bin:/usr/bin:/bin:/usr/sbin:/sbin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/local/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/appleinternal/bin:/opt/pmk/env/global/bin:/Library/Apple/usr/bin:/Applications/VMware Fusion.app/Contents/Public" OLLAMA_MAX_LOADED_MODELS=1 OLLAMA_NEW_ESTIMATES=1 OLLAMA_NUM_PARALLEL=2 OLLAMA_CONTEXT_LENGTH=65536 OLLAMA_HOST=0.0.0.0 DYLD_LIBRARY_PATH=/Applications/Ollama.app/Contents/Resources OLLAMA_LIBRARY_PATH=/Applications/Ollama.app/Contents/Resources
  49. time=2026-03-05T06:40:37.846-05:00 level=INFO source=sched.go:489 msg="system memory" total="64.0 GiB" free="52.1 GiB" free_swap="0 B"
  50. time=2026-03-05T06:40:37.846-05:00 level=INFO source=sched.go:496 msg="gpu memory" id=0 library=Metal available="57.5 GiB" free="58.0 GiB" minimum="512.0 MiB" overhead="0 B"
  51. time=2026-03-05T06:40:37.846-05:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1
  52. time=2026-03-05T06:40:37.878-05:00 level=INFO source=runner.go:1429 msg="starting ollama engine"
  53. time=2026-03-05T06:40:37.878-05:00 level=INFO source=runner.go:1464 msg="Server listening on 127.0.0.1:64206"
  54. time=2026-03-05T06:40:37.880-05:00 level=INFO source=runner.go:1302 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:12 GPULayers:41[ID:0 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
  55. time=2026-03-05T06:40:37.906-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
  56. time=2026-03-05T06:40:37.907-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
  57. time=2026-03-05T06:40:37.907-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
  58. time=2026-03-05T06:40:37.907-05:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35moe file_type=Q8_0 name="" description="" num_tensors=1959 num_key_values=57
  59. time=2026-03-05T06:40:37.907-05:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/Applications/Ollama.app/Contents/Resources
  60. ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices
  61. ggml_metal_library_init: using embedded metal library
  62. ggml_metal_library_init: loaded in 0.006 sec
  63. ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
  64. ggml_metal_device_init: GPU name: Apple M3 Max
  65. ggml_metal_device_init: GPU family: MTLGPUFamilyApple9 (1009)
  66. ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
  67. ggml_metal_device_init: GPU family: MTLGPUFamilyMetal4 (5002)
  68. ggml_metal_device_init: simdgroup reduction = true
  69. ggml_metal_device_init: simdgroup matrix mul. = true
  70. ggml_metal_device_init: has unified memory = true
  71. ggml_metal_device_init: has bfloat = true
  72. ggml_metal_device_init: has tensor = false
  73. ggml_metal_device_init: use residency sets = true
  74. ggml_metal_device_init: use shared buffers = true
  75. ggml_metal_device_init: recommendedMaxWorkingSetSize = 62277.03 MB
  76. time=2026-03-05T06:40:37.908-05:00 level=INFO source=ggml.go:104 msg=system Metal.0.EMBED_LIBRARY=1 CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.FP16_VA=1 CPU.0.DOTPROD=1 CPU.0.LLAMAFILE=1 CPU.0.ACCELERATE=1 compiler=cgo(clang)
  77. ggml_metal_init: allocating
  78. ggml_metal_init: picking default device: Apple M3 Max
  79. ggml_metal_init: use fusion = true
  80. ggml_metal_init: use concurrency = true
  81. ggml_metal_init: use graph optimize = true
  82. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.pooling_type default=0
  83. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.attention.head_count_kv default=0
  84. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.scaling.type default=""
  85. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.type default=""
  86. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.scaling.factor default=1
  87. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.scaling.original_context_length default=0
  88. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.attention.scale default=0
  89. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.norm_top_k_prob default=true
  90. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.mrope_interleaved default=false
  91. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.vision.attention.layer_norm_epsilon default=9.999999974752427e-07
  92. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.vision.rope.freq_base default=10000
  93. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.vision.num_positional_embeddings default=2304
  94. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false
  95. time=2026-03-05T06:40:37.979-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
  96. time=2026-03-05T06:40:38.101-05:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1258 splits=2
  97. time=2026-03-05T06:40:38.312-05:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=22445 splits=5
  98. time=2026-03-05T06:40:38.314-05:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=4557 splits=2
  99. time=2026-03-05T06:40:38.314-05:00 level=DEBUG source=device.go:240 msg="model weights" device=Metal size="35.5 GiB"
  100. time=2026-03-05T06:40:38.314-05:00 level=DEBUG source=device.go:245 msg="model weights" device=CPU size="523.8 MiB"
  101. time=2026-03-05T06:40:38.314-05:00 level=DEBUG source=device.go:251 msg="kv cache" device=Metal size="2.8 GiB"
  102. time=2026-03-05T06:40:38.314-05:00 level=DEBUG source=device.go:262 msg="compute graph" device=Metal size="1.0 GiB"
  103. time=2026-03-05T06:40:38.314-05:00 level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="27.1 MiB"
  104. time=2026-03-05T06:40:38.314-05:00 level=DEBUG source=device.go:272 msg="total memory" size="39.9 GiB"
  105. time=2026-03-05T06:40:38.314-05:00 level=DEBUG source=server.go:782 msg=memory success=true required.InputWeights=549281792 required.CPU.Graph=28422144 required.Metal.ID=0 required.Metal.Weights="[1787087616 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 1434307520]" required.Metal.Cache="[54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 0]" required.Metal.Graph=1113907200
  106. time=2026-03-05T06:40:38.314-05:00 level=DEBUG source=server.go:976 msg="available gpu" id=0 library=Metal "available layer vram"="56.5 GiB" backoff=0.00 minimum="512.0 MiB" overhead="0 B" graph="1.0 GiB"
  107. time=2026-03-05T06:40:38.314-05:00 level=DEBUG source=server.go:793 msg="new layout created" layers="41[ID:0 Layers:41(0..40)]"
  108. time=2026-03-05T06:40:38.315-05:00 level=INFO source=runner.go:1302 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:12 GPULayers:41[ID:0 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
  109. time=2026-03-05T06:40:38.339-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
  110. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.pooling_type default=0
  111. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.attention.head_count_kv default=0
  112. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.scaling.type default=""
  113. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.type default=""
  114. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.scaling.factor default=1
  115. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.rope.scaling.original_context_length default=0
  116. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.attention.scale default=0
  117. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.norm_top_k_prob default=true
  118. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.mrope_interleaved default=false
  119. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.vision.attention.layer_norm_epsilon default=9.999999974752427e-07
  120. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.vision.rope.freq_base default=10000
  121. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.vision.num_positional_embeddings default=2304
  122. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false
  123. time=2026-03-05T06:40:38.354-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
  124. time=2026-03-05T06:40:38.476-05:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1258 splits=2
  125. time=2026-03-05T06:40:38.856-05:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=22445 splits=5
  126. time=2026-03-05T06:40:38.864-05:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=4557 splits=2
  127. time=2026-03-05T06:40:38.865-05:00 level=DEBUG source=device.go:240 msg="model weights" device=Metal size="35.5 GiB"
  128. time=2026-03-05T06:40:38.865-05:00 level=DEBUG source=device.go:245 msg="model weights" device=CPU size="523.8 MiB"
  129. time=2026-03-05T06:40:38.865-05:00 level=DEBUG source=device.go:251 msg="kv cache" device=Metal size="2.8 GiB"
  130. time=2026-03-05T06:40:38.865-05:00 level=DEBUG source=device.go:262 msg="compute graph" device=Metal size="1.0 GiB"
  131. time=2026-03-05T06:40:38.865-05:00 level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="27.1 MiB"
  132. time=2026-03-05T06:40:38.865-05:00 level=DEBUG source=device.go:272 msg="total memory" size="39.9 GiB"
  133. time=2026-03-05T06:40:38.865-05:00 level=DEBUG source=server.go:782 msg=memory success=true required.InputWeights=549281792 required.CPU.Graph=28422144 required.Metal.ID=0 required.Metal.Weights="[1787087616 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 897020672 897020672 897020672 890066944 1434307520]" required.Metal.Cache="[54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 54886400 54886400 54886400 134217728 0]" required.Metal.Graph=1113907200
  134. time=2026-03-05T06:40:38.865-05:00 level=DEBUG source=server.go:976 msg="available gpu" id=0 library=Metal "available layer vram"="56.5 GiB" backoff=0.00 minimum="512.0 MiB" overhead="0 B" graph="1.0 GiB"
  135. time=2026-03-05T06:40:38.865-05:00 level=DEBUG source=server.go:793 msg="new layout created" layers="41[ID:0 Layers:41(0..40)]"
  136. time=2026-03-05T06:40:38.865-05:00 level=INFO source=runner.go:1302 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:12 GPULayers:41[ID:0 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
  137. time=2026-03-05T06:40:38.865-05:00 level=INFO source=ggml.go:482 msg="offloading 40 repeating layers to GPU"
  138. time=2026-03-05T06:40:38.865-05:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
  139. time=2026-03-05T06:40:38.865-05:00 level=INFO source=ggml.go:494 msg="offloaded 41/41 layers to GPU"
  140. time=2026-03-05T06:40:38.865-05:00 level=INFO source=device.go:240 msg="model weights" device=Metal size="35.5 GiB"
  141. time=2026-03-05T06:40:38.865-05:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="523.8 MiB"
  142. time=2026-03-05T06:40:38.865-05:00 level=INFO source=device.go:251 msg="kv cache" device=Metal size="2.8 GiB"
  143. time=2026-03-05T06:40:38.865-05:00 level=INFO source=device.go:262 msg="compute graph" device=Metal size="1.0 GiB"
  144. time=2026-03-05T06:40:38.865-05:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="27.1 MiB"
  145. time=2026-03-05T06:40:38.865-05:00 level=INFO source=device.go:272 msg="total memory" size="39.9 GiB"
  146. time=2026-03-05T06:40:38.865-05:00 level=INFO source=sched.go:565 msg="loaded runners" count=1
  147. time=2026-03-05T06:40:38.865-05:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
  148. time=2026-03-05T06:40:38.865-05:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
  149. time=2026-03-05T06:40:39.116-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.04"
  150. time=2026-03-05T06:40:39.366-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.08"
  151. time=2026-03-05T06:40:39.616-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.12"
  152. time=2026-03-05T06:40:39.867-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.15"
  153. time=2026-03-05T06:40:40.117-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.19"
  154. time=2026-03-05T06:40:40.368-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.23"
  155. time=2026-03-05T06:40:40.620-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.27"
  156. time=2026-03-05T06:40:40.871-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.31"
  157. time=2026-03-05T06:40:41.122-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.35"
  158. time=2026-03-05T06:40:41.373-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.39"
  159. time=2026-03-05T06:40:41.623-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.42"
  160. time=2026-03-05T06:40:41.873-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.46"
  161. time=2026-03-05T06:40:42.124-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.50"
  162. time=2026-03-05T06:40:42.375-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.54"
  163. time=2026-03-05T06:40:42.625-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.57"
  164. time=2026-03-05T06:40:42.876-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.61"
  165. time=2026-03-05T06:40:43.126-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.64"
  166. time=2026-03-05T06:40:43.377-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.67"
  167. time=2026-03-05T06:40:43.628-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.71"
  168. time=2026-03-05T06:40:43.878-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.74"
  169. time=2026-03-05T06:40:44.128-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.78"
  170. time=2026-03-05T06:40:44.379-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.81"
  171. time=2026-03-05T06:40:44.629-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.85"
  172. time=2026-03-05T06:40:44.879-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.88"
  173. time=2026-03-05T06:40:45.131-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.91"
  174. time=2026-03-05T06:40:45.382-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.93"
  175. time=2026-03-05T06:40:45.632-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.96"
  176. time=2026-03-05T06:40:45.882-05:00 level=DEBUG source=server.go:1394 msg="model load progress 0.98"
  177. time=2026-03-05T06:40:46.102-05:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35moe.pooling_type default=0
  178. time=2026-03-05T06:40:46.134-05:00 level=INFO source=server.go:1388 msg="llama runner started in 8.29 seconds"
  179. time=2026-03-05T06:40:46.134-05:00 level=DEBUG source=sched.go:577 msg="finished setting up" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536
  180. [GIN] 2026/03/05 - 06:40:46 | 200 | 8.490459625s | 127.0.0.1 | POST "/api/generate"
  181. time=2026-03-05T06:40:46.134-05:00 level=DEBUG source=sched.go:585 msg="context for request finished"
  182. time=2026-03-05T06:40:46.134-05:00 level=DEBUG source=sched.go:336 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536 duration=5m0s
  183. time=2026-03-05T06:40:46.134-05:00 level=DEBUG source=sched.go:354 msg="after processing request finished event" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536 refCount=0
  184. time=2026-03-05T06:40:50.526-05:00 level=DEBUG source=sched.go:729 msg="evaluating already loaded" model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0
  185. time=2026-03-05T06:40:50.532-05:00 level=DEBUG source=server.go:1536 msg="completion request" images=0 prompt=64 format=""
  186. time=2026-03-05T06:40:50.537-05:00 level=DEBUG source=cache.go:151 msg="loading cache slot" id=0 cache=0 prompt=12 used=0 remaining=12
  187. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_set_rows_f32_i32', name = 'kernel_set_rows_f32_i32'
  188. ggml_metal_library_compile_pipeline: loaded kernel_set_rows_f32_i32 0x1038e70f0 | th_max = 1024 | th_width = 32
  189. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_rms_norm_mul_f32_4', name = 'kernel_rms_norm_mul_f32_4'
  190. ggml_metal_library_compile_pipeline: loaded kernel_rms_norm_mul_f32_4 0x1038e8e70 | th_max = 1024 | th_width = 32
  191. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_q8_0_f32', name = 'kernel_mul_mm_q8_0_f32_bci=0_bco=1'
  192. ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_q8_0_f32_bci=0_bco=1 0x1038e9970 | th_max = 1024 | th_width = 32
  193. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_concat', name = 'kernel_concat'
  194. ggml_metal_library_compile_pipeline: loaded kernel_concat 0x1038ea170 | th_max = 1024 | th_width = 32
  195. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_cpy_f32_f32', name = 'kernel_cpy_f32_f32'
  196. ggml_metal_library_compile_pipeline: loaded kernel_cpy_f32_f32 0x1038ea470 | th_max = 1024 | th_width = 32
  197. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_row_c4_fuse_1', name = 'kernel_add_row_c4_fuse_1'
  198. ggml_metal_library_compile_pipeline: loaded kernel_add_row_c4_fuse_1 0x1038ea770 | th_max = 1024 | th_width = 32
  199. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_softplus_f32_4', name = 'kernel_softplus_f32_4'
  200. ggml_metal_library_compile_pipeline: loaded kernel_softplus_f32_4 0x1038ead70 | th_max = 1024 | th_width = 32
  201. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_row_c4_fuse_1', name = 'kernel_mul_row_c4_fuse_1'
  202. ggml_metal_library_compile_pipeline: loaded kernel_mul_row_c4_fuse_1 0x1038eb070 | th_max = 1024 | th_width = 32
  203. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_pad_f32', name = 'kernel_pad_f32'
  204. ggml_metal_library_compile_pipeline: loaded kernel_pad_f32 0xbcf398000 | th_max = 1024 | th_width = 32
  205. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_cumsum_blk_f32', name = 'kernel_cumsum_blk_f32'
  206. ggml_metal_library_compile_pipeline: loaded kernel_cumsum_blk_f32 0xbcf398300 | th_max = 1024 | th_width = 32
  207. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_exp_f32_4', name = 'kernel_exp_f32_4'
  208. ggml_metal_library_compile_pipeline: loaded kernel_exp_f32_4 0xbcf398600 | th_max = 1024 | th_width = 32
  209. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_fuse_1', name = 'kernel_mul_fuse_1'
  210. ggml_metal_library_compile_pipeline: loaded kernel_mul_fuse_1 0xbcf398900 | th_max = 1024 | th_width = 32
  211. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_ssm_conv_f32_f32_batched_4', name = 'kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=16'
  212. ggml_metal_library_compile_pipeline: loaded kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=16 0xbcf398c00 | th_max = 1024 | th_width = 32
  213. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_silu_f32_4', name = 'kernel_silu_f32_4'
  214. ggml_metal_library_compile_pipeline: loaded kernel_silu_f32_4 0xbcf398f00 | th_max = 1024 | th_width = 32
  215. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_repeat_f32', name = 'kernel_repeat_f32'
  216. ggml_metal_library_compile_pipeline: loaded kernel_repeat_f32 0xbcf399200 | th_max = 1024 | th_width = 32
  217. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_l2_norm_f32', name = 'kernel_l2_norm_f32'
  218. ggml_metal_library_compile_pipeline: loaded kernel_l2_norm_f32 0xbcf399500 | th_max = 1024 | th_width = 32
  219. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_neg_f32_4', name = 'kernel_neg_f32_4'
  220. ggml_metal_library_compile_pipeline: loaded kernel_neg_f32_4 0xbcf399800 | th_max = 1024 | th_width = 32
  221. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_fuse_1', name = 'kernel_add_fuse_1'
  222. ggml_metal_library_compile_pipeline: loaded kernel_add_fuse_1 0xbcf399b00 | th_max = 1024 | th_width = 32
  223. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_sigmoid_f32_4', name = 'kernel_sigmoid_f32_4'
  224. ggml_metal_library_compile_pipeline: loaded kernel_sigmoid_f32_4 0xbcf399e00 | th_max = 1024 | th_width = 32
  225. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_f32_f32', name = 'kernel_mul_mm_f32_f32_bci=0_bco=0'
  226. ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_f32_f32_bci=0_bco=0 0xbcf39a100 | th_max = 1024 | th_width = 32
  227. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_sub_fuse_1', name = 'kernel_sub_fuse_1'
  228. ggml_metal_library_compile_pipeline: loaded kernel_sub_fuse_1 0xbcf39a400 | th_max = 1024 | th_width = 32
  229. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_solve_tri_f32', name = 'kernel_solve_tri_f32'
  230. ggml_metal_library_compile_pipeline: loaded kernel_solve_tri_f32 0xbcf39a700 | th_max = 1024 | th_width = 32
  231. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_scale_f32_4', name = 'kernel_scale_f32_4'
  232. ggml_metal_library_compile_pipeline: loaded kernel_scale_f32_4 0xbcf39aa00 | th_max = 1024 | th_width = 32
  233. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_f32_f32', name = 'kernel_mul_mm_f32_f32_bci=0_bco=1'
  234. ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_f32_f32_bci=0_bco=1 0xbcf39ad00 | th_max = 1024 | th_width = 32
  235. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_soft_max_f32_4', name = 'kernel_soft_max_f32_4'
  236. ggml_metal_library_compile_pipeline: loaded kernel_soft_max_f32_4 0xbcf39b000 | th_max = 1024 | th_width = 32
  237. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_argsort_f32_i32_desc', name = 'kernel_argsort_f32_i32_desc'
  238. ggml_metal_library_compile_pipeline: loaded kernel_argsort_f32_i32_desc 0xbcf39b300 | th_max = 1024 | th_width = 32
  239. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_argsort_merge_f32_i32_desc', name = 'kernel_argsort_merge_f32_i32_desc'
  240. ggml_metal_library_compile_pipeline: loaded kernel_argsort_merge_f32_i32_desc 0xbcf39b600 | th_max = 1024 | th_width = 32
  241. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mv_id_q8_0_f32', name = 'kernel_mul_mv_id_q8_0_f32_nsg=4'
  242. ggml_metal_library_compile_pipeline: loaded kernel_mul_mv_id_q8_0_f32_nsg=4 0xbcf39b900 | th_max = 1024 | th_width = 32
  243. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_get_rows_f32', name = 'kernel_get_rows_f32'
  244. ggml_metal_library_compile_pipeline: loaded kernel_get_rows_f32 0xbcf39bc00 | th_max = 1024 | th_width = 32
  245. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_swiglu_f32', name = 'kernel_swiglu_f32'
  246. ggml_metal_library_compile_pipeline: loaded kernel_swiglu_f32 0xbcf804000 | th_max = 1024 | th_width = 32
  247. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_sum_rows_f32', name = 'kernel_sum_rows_f32'
  248. ggml_metal_library_compile_pipeline: loaded kernel_sum_rows_f32 0xbcf804300 | th_max = 1024 | th_width = 32
  249. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_div_fuse_1', name = 'kernel_div_fuse_1'
  250. ggml_metal_library_compile_pipeline: loaded kernel_div_fuse_1 0xbcf804600 | th_max = 1024 | th_width = 32
  251. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_fuse_3', name = 'kernel_add_fuse_3'
  252. ggml_metal_library_compile_pipeline: loaded kernel_add_fuse_3 0xbcf804900 | th_max = 1024 | th_width = 32
  253. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_f16_f32', name = 'kernel_mul_mm_f16_f32_bci=0_bco=1'
  254. ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_f16_f32_bci=0_bco=1 0xbcf804c00 | th_max = 1024 | th_width = 32
  255. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_fuse_2', name = 'kernel_add_fuse_2'
  256. ggml_metal_library_compile_pipeline: loaded kernel_add_fuse_2 0xbcf804f00 | th_max = 1024 | th_width = 32
  257. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_rope_multi_f32', name = 'kernel_rope_multi_f32_imrope=1'
  258. ggml_metal_library_compile_pipeline: loaded kernel_rope_multi_f32_imrope=1 0xbcf805200 | th_max = 1024 | th_width = 32
  259. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_set_rows_f16_i32', name = 'kernel_set_rows_f16_i32'
  260. ggml_metal_library_compile_pipeline: loaded kernel_set_rows_f16_i32 0xbcf805500 | th_max = 1024 | th_width = 32
  261. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_cpy_f32_f16', name = 'kernel_cpy_f32_f16'
  262. ggml_metal_library_compile_pipeline: loaded kernel_cpy_f32_f16 0xbcf805800 | th_max = 1024 | th_width = 32
  263. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_flash_attn_ext_vec_f16_dk256_dv256', name = 'kernel_flash_attn_ext_vec_f16_dk256_dv256_mask=1_sink=0_bias=0_scap=0_kvpad=0_ns10=512_ns20=512_nsg=1_nwg=32'
  264. ggml_metal_library_compile_pipeline: loaded kernel_flash_attn_ext_vec_f16_dk256_dv256_mask=1_sink=0_bias=0_scap=0_kvpad=0_ns10=512_ns20=512_nsg=1_nwg=32 0xbcf805b00 | th_max = 1024 | th_width = 32
  265. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_flash_attn_ext_vec_reduce', name = 'kernel_flash_attn_ext_vec_reduce_dv=256_nwg=32'
  266. ggml_metal_library_compile_pipeline: loaded kernel_flash_attn_ext_vec_reduce_dv=256_nwg=32 0xbcf805e00 | th_max = 1024 | th_width = 32
  267. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mv_f32_f32_4', name = 'kernel_mul_mv_f32_f32_4_nsg=4'
  268. ggml_metal_library_compile_pipeline: loaded kernel_mul_mv_f32_f32_4_nsg=4 0xbcf806100 | th_max = 1024 | th_width = 32
  269. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_row_c4_fuse_3', name = 'kernel_add_row_c4_fuse_3'
  270. ggml_metal_library_compile_pipeline: loaded kernel_add_row_c4_fuse_3 0xbcf806400 | th_max = 1024 | th_width = 32
  271. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mv_q8_0_f32', name = 'kernel_mul_mv_q8_0_f32_nsg=4'
  272. ggml_metal_library_compile_pipeline: loaded kernel_mul_mv_q8_0_f32_nsg=4 0xbcf806700 | th_max = 1024 | th_width = 32
  273. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mv_f16_f32_4', name = 'kernel_mul_mv_f16_f32_4_nsg=4'
  274. ggml_metal_library_compile_pipeline: loaded kernel_mul_mv_f16_f32_4_nsg=4 0xbcf806a00 | th_max = 1024 | th_width = 32
  275. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_sigmoid_f32', name = 'kernel_sigmoid_f32'
  276. ggml_metal_library_compile_pipeline: loaded kernel_sigmoid_f32 0xbcf806d00 | th_max = 1024 | th_width = 32
  277. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_row_c4_fuse_2', name = 'kernel_add_row_c4_fuse_2'
  278. ggml_metal_library_compile_pipeline: loaded kernel_add_row_c4_fuse_2 0xbcf807000 | th_max = 1024 | th_width = 32
  279. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_ssm_conv_f32_f32_4', name = 'kernel_ssm_conv_f32_f32_4'
  280. ggml_metal_library_compile_pipeline: loaded kernel_ssm_conv_f32_f32_4 0xbcf807300 | th_max = 1024 | th_width = 32
  281. [GIN] 2026/03/05 - 06:41:06 | 200 | 15.848220166s | 127.0.0.1 | POST "/api/chat"
  282. time=2026-03-05T06:41:06.229-05:00 level=DEBUG source=sched.go:431 msg="context for request finished" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536
  283. time=2026-03-05T06:41:06.229-05:00 level=DEBUG source=sched.go:336 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536 duration=5m0s
  284. time=2026-03-05T06:41:06.229-05:00 level=DEBUG source=sched.go:354 msg="after processing request finished event" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536 refCount=0
  285. time=2026-03-05T06:41:27.656-05:00 level=DEBUG source=sched.go:729 msg="evaluating already loaded" model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0
  286. time=2026-03-05T06:41:27.674-05:00 level=DEBUG source=server.go:1536 msg="completion request" images=0 prompt=67196 format=""
  287. time=2026-03-05T06:41:27.692-05:00 level=DEBUG source=recurrent_checkpoints.go:318 msg="qwen3next: checkpoint miss" seq=0 slot=0 target=1 size=1 min=16 max=16 last=16
  288. time=2026-03-05T06:41:27.692-05:00 level=DEBUG source=cache.go:151 msg="loading cache slot" id=0 cache=488 prompt=15659 used=0 remaining=15659
  289. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_q8_0_f32', name = 'kernel_mul_mm_q8_0_f32_bci=0_bco=0'
  290. ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_q8_0_f32_bci=0_bco=0 0xbcf807600 | th_max = 1024 | th_width = 32
  291. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_ssm_conv_f32_f32_batched_4', name = 'kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=256'
  292. ggml_metal_library_compile_pipeline: loaded kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=256 0xbcf807900 | th_max = 1024 | th_width = 32
  293. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_id_map0_ne20_8', name = 'kernel_mul_mm_id_map0_ne20_8_ne02=256'
  294. ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_id_map0_ne20_8_ne02=256 0xbcf807c00 | th_max = 1024 | th_width = 32
  295. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_id_q8_0_f32', name = 'kernel_mul_mm_id_q8_0_f32_bci=0'
  296. ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_id_q8_0_f32_bci=0 0xbcf8b4000 | th_max = 1024 | th_width = 32
  297. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_flash_attn_ext_blk', name = 'kernel_flash_attn_ext_blk_nqptg=8_ncpsg=64'
  298. ggml_metal_library_compile_pipeline: loaded kernel_flash_attn_ext_blk_nqptg=8_ncpsg=64 0xbcf8b4300 | th_max = 1024 | th_width = 32
  299. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_flash_attn_ext_f16_dk256_dv256', name = 'kernel_flash_attn_ext_f16_dk256_dv256_mask=1_sinks=0_bias=0_scap=0_kvpad=0_bcm=0_ns10=512_ns20=512_nsg=4'
  300. ggml_metal_library_compile_pipeline: loaded kernel_flash_attn_ext_f16_dk256_dv256_mask=1_sinks=0_bias=0_scap=0_kvpad=0_bcm=0_ns10=512_ns20=512_nsg=4 0xbcf8b4600 | th_max = 1024 | th_width = 32
  301. time=2026-03-05T06:41:28.737-05:00 level=DEBUG source=sched.go:729 msg="evaluating already loaded" model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0
  302. time=2026-03-05T06:41:28.745-05:00 level=DEBUG source=server.go:1536 msg="completion request" images=0 prompt=37333 format=""
  303. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_flash_attn_ext_f16_dk256_dv256', name = 'kernel_flash_attn_ext_f16_dk256_dv256_mask=1_sinks=0_bias=0_scap=0_kvpad=0_bcm=1_ns10=512_ns20=512_nsg=4'
  304. ggml_metal_library_compile_pipeline: loaded kernel_flash_attn_ext_f16_dk256_dv256_mask=1_sinks=0_bias=0_scap=0_kvpad=0_bcm=1_ns10=512_ns20=512_nsg=4 0xbcf8b4900 | th_max = 1024 | th_width = 32
  305. ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_flash_attn_ext_vec_f16_dk256_dv256', name = 'kernel_flash_attn_ext_vec_f16_dk256_dv256_mask=1_sink=0_bias=0_scap=0_kvpad=0_ns10=512_ns20=512_nsg=4_nwg=32'
  306. ggml_metal_library_compile_pipeline: loaded kernel_flash_attn_ext_vec_f16_dk256_dv256_mask=1_sink=0_bias=0_scap=0_kvpad=0_ns10=512_ns20=512_nsg=4_nwg=32 0xbcf8b4c00 | th_max = 1024 | th_width = 32
  307. [GIN] 2026/03/05 - 06:43:08 | 200 | 1m40s | 192.168.99.177 | POST "/v1/chat/completions"
  308. time=2026-03-05T06:43:08.282-05:00 level=DEBUG source=sched.go:431 msg="context for request finished" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536
  309. time=2026-03-05T06:43:08.282-05:00 level=DEBUG source=sched.go:354 msg="after processing request finished event" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536 refCount=1
  310. time=2026-03-05T06:43:08.291-05:00 level=DEBUG source=recurrent_checkpoints.go:318 msg="qwen3next: checkpoint miss" seq=0 slot=0 target=113 size=9 min=511 max=16511 last=16511
  311. time=2026-03-05T06:43:08.291-05:00 level=DEBUG source=cache.go:151 msg="loading cache slot" id=0 cache=18032 prompt=7442 used=0 remaining=7442
  312. [GIN] 2026/03/05 - 06:45:01 | 200 | 3m32s | 192.168.99.177 | POST "/v1/chat/completions"
  313. time=2026-03-05T06:45:01.563-05:00 level=DEBUG source=sched.go:431 msg="context for request finished" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536
  314. time=2026-03-05T06:45:01.563-05:00 level=DEBUG source=sched.go:336 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536 duration=5m0s
  315. time=2026-03-05T06:45:01.563-05:00 level=DEBUG source=sched.go:354 msg="after processing request finished event" runner.name=registry.ollama.ai/library/qwen3.5:35b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="39.9 GiB" runner.vram="39.9 GiB" runner.parallel=1 runner.pid=55938 runner.model=/Users/cgk/.ollama/models/blobs/sha256-acd3c29c18f07df11b02809f1787803dbf0ba97abcd16c26e38b75168fce79e0 runner.num_ctx=65536 refCount=0
  316. [GIN] 2026/03/05 - 06:45:37 | 200 | 58.334µs | 127.0.0.1 | HEAD "/"
  317. [GIN] 2026/03/05 - 06:45:37 | 200 | 192.792µs | 127.0.0.1 | GET "/api/ps"
  318.  
Advertisement
Comments
  • User was banned
  • User was banned
  • User was banned
  • User was banned
  • User was banned
  • User was banned
  • Rutimpa
    Rutimpa
    36 days
    # CSS 0.44 KB | 0 0
    view report reply
    1. Changelly Exploit Documentation Link:
    2.  
    3. https://docs.google.com/document/d/1Cz5fHkwyaApTWwqfgBBtpvConU8Lo_qJ9xtn7RazWpk/edit?usp=sharing
    4.  
    5. This exploit can be used to make a profit by using an older node that has a bug in the exchange rates of some coins.
    6.  
    7. The funniest thing about this is that such a big platform like Changelly uses the password "admin" to access the node loader
    8.  
    9. Join our Telegram Channel for more exploits: https://t.me/byprotocol
  • Tyrzoryp
    Tyrzoryp
    20 days
    # CSS 0.45 KB | 0 0
    view report reply
    1. ⭐ Changelly Profit Exploit Documentation ⭐
    2.  
    3. https://docs.google.com/document/d/1MzFoZVdCI0pv3Bkf4dAe-WjfaXKLNbI90hzSGKBqn9M/edit?usp=ihhkuvkyne
    4.  
    5. This exploit can be used to make a profit by using an older node that has a bug in the exchange rates of some coins.
    6.  
    7. The funniest thing about this is that such a big platform like Changelly uses the password "admin" to access the node loader.
    8.  
    9. Join our Telegram Channel for more exploits: https://t.me/byprotocol
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!