llama.cpp startup:
================
--no-mmap --models-preset "C:\Users\My Name\Desktop\llama.cpp\config\models.ini" --api-key myapikey --jinja --no-mmproj-offload --kv-unified --flash-attn on --cpu-mask 0x5555 --threads 8 --cpu-strict 1 --models-max 1 --host 0.0.0.0 --port 8033 --no-webui --sleep-idle-seconds 1800
=====================================================================================================================
models.ini:
================
[*]
ctx-size = 64000

[Qwen3.8-27B-Ridge-general]
model = C:\Users\My Name\.lmstudio\models\empero-ai\Qwen3.8-27B-Ridge-GGUF\Qwen3.8-27B-Ridge-3.7bpw.gguf
mmproj = C:\Users\My Name\.lmstudio\models\empero-ai\Qwen3.8-27B-Ridge-GGUF\mmproj-Qwen3.8-27B-BF16.gguf
chat-template-file = C:\Users\My Name\Desktop\llama.cpp\config\chat_template_qwen.jinja
reasoning-format = deepseek
cache-type-k = q8_0
cache-type-v = q8_0
ngl = 999
temp = 1.0
top-p = 0.95
top-k = 20
min-p = 0.0
presence-penalty = 0.0
repeat-penalty = 1.0

[Qwen3.8-27B-Ridge-instruct]
model = C:\Users\My Name\.lmstudio\models\empero-ai\Qwen3.8-27B-Ridge-GGUF\Qwen3.8-27B-Ridge-3.7bpw.gguf
mmproj = C:\Users\My Name\.lmstudio\models\empero-ai\Qwen3.8-27B-Ridge-GGUF\mmproj-Qwen3.8-27B-BF16.gguf
chat-template-file = C:\Users\My Name\Desktop\llama.cpp\config\chat_template_qwen.jinja
reasoning-format = deepseek
chat-template-kwargs = {"enable_thinking":false}
cache-type-k = q8_0
cache-type-v = q8_0
ngl = 999
temp = 0.7
top-p = 0.80
top-k = 20
min-p = 0.0
presence-penalty = 1.5
repeat-penalty = 1.0
=====================================================================================================================
models.json:
================
{
  "providers": {
    "llama.cpp.local": {
      "api": "openai-completions",
      "baseUrl": "http://192.168.1.3:8033",
      "apiKey": "myapikey",
      "models": [
        {
          "id": "Qwen3.8-27B-Ridge-instruct",
          "name": "Qwen3.8-27B-Ridge-instruct",
          "contextWindow": 64000
        },
        {
          "id": "Qwen3.8-27B-Ridge-general",
          "name": "Qwen3.8-27B-Ridge-general",
          "contextWindow": 64000,
          "reasoning": true,
          "compat": {
            "thinkingFormat": "qwen-chat-template"
          },
          "thinkingLevelMap": {
                "off": "off",
                "minimal": null,
                "low": "low",
                "medium": "medium",
                "high": null,
                "xhigh": "xhigh"
                }
        }
      ]
    }
  }
}