diff --git a/apps/llama/configs/config.yaml b/apps/llama/configs/config.yaml index ecc1cee..dedb58b 100644 --- a/apps/llama/configs/config.yaml +++ b/apps/llama/configs/config.yaml @@ -88,6 +88,16 @@ models: ${qwen35_35b_args} ${common_args} + "Qwen3.5-35B-A3B-GGUF-CPU:Q4_K_M": + cmd: | + /app/llama-server + -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M + ${ctx_256k} + ${qwen35_35b_args} + --threads 12 + -ngl 0 + ${common_args} + "Qwen3.5-35B-A3B-GGUF-nothink:Q4_K_M": cmd: | /app/llama-server