John Ogle
10efafd92e
- Add local-inference NixOS role using llama-swap (from nixpkgs-unstable) with llama.cpp (CUDA-enabled, from nixpkgs-unstable) - Serves Qwen3.6-35B-A3B via HuggingFace auto-download with --cpu-moe - Add nixosSpecialArgs for nixpkgs-unstable module access - Configure opencode with llama-local provider pointing to zix790prors:8080 - Update gptel from Ollama backend to OpenAI-compatible llama-swap backend - Remove ollama service from zix790prors
23 lines
541 B
JSON
23 lines
541 B
JSON
{
|
|
"$schema": "https://opencode.ai/config.json",
|
|
"provider": {
|
|
"llama-local": {
|
|
"name": "Llama.cpp (zix790prors RTX 4070 Ti)",
|
|
"npm": "@ai-sdk/openai-compatible",
|
|
"options": {
|
|
"baseURL": "http://zix790prors.oglehome:8080/v1"
|
|
},
|
|
"models": {
|
|
"Qwen3.6-35B-A3B": {
|
|
"name": "Qwen3.6-35B-A3B (UD-Q8_K_XL)",
|
|
"reasoning": true,
|
|
"tool_call": true,
|
|
"limit": {
|
|
"context": 32768,
|
|
"output": 8192
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |