diff --git a/apps/llama/configs/config.yaml b/apps/llama/configs/config.yaml index 44bf028..06e40a7 100644 --- a/apps/llama/configs/config.yaml +++ b/apps/llama/configs/config.yaml @@ -538,3 +538,18 @@ models: --presence-penalty 1.5 --no-warmup --port ${PORT} + + "gemma-3-270m-it-qat-GGUF:Q4_K_M": + ttl: 600 + cmd: | + /app/llama-server + -hf unsloth/gemma-3-270m-it-qat-GGUF:Q4_K_M + --ctx-size 16384 + --predict 4096 + --temp 1.0 + --min-p 0.01 + --top-p 0.95 + --top-k 64 + --repeat-penalty 1.0 + --no-warmup + --port ${PORT}