Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- S:\beellama.cpp-win\build-msvc-cuda-server\bin\llama-server ^
- --model A:\models\Qwen3.6-27B-Q2_K_MIXED-AutoRound-MTP.gguf ^
- --ctx-size 160000 ^
- --spec-draft-model "S:\LLMs\Qwen3.6-27B-DFlash-IQ4_XS.gguf" ^
- --spec-type dflash ^
- --spec-dflash-cross-ctx 1024 ^
- --spec-draft-ngl all ^
- --batch-size 2048 ^
- --gpu-layers all ^
- --cache-type-k q8_0 --cache-type-v q8_0 ^
- --spec-draft-type-k q8_0 --spec-draft-type-v q8_0 ^
- --jinja ^
- --no-mmap ^
- --mlock ^
- --main-gpu 1 --split-mode layer --tensor-split 54,46 ^
- --ctx-checkpoints 32 --checkpoint-min-step 1024 ^
- --parallel 1 --kv-unified ^
- --cache-ram 8192 ^
- --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0.0 ^
- --repeat-penalty 1.0 ^
- --presence-penalty 0.0
Advertisement
Add Comment
Please, Sign In to add comment