26 lines
781 B
Bash
26 lines
781 B
Bash
|
# Profile: mid — ~8GB AMD GPU + 16GB system RAM
|
||
|
|
# Vulkan offload; use Qwen3.5-9B Abliterated Q4_K_M (~5.6GB) for VRAM fit.
|
||
|
|
STACK_PROFILE=mid
|
||
|
|
|
||
|
|
BONSAI_BACKEND=vulkan
|
||
|
|
BONSAI_NGL=99
|
||
|
|
BONSAI_CTX=8192
|
||
|
|
BONSAI_KV4=1
|
||
|
|
BONSAI_THREADS=8
|
||
|
|
BONSAI_TEMP=0.7
|
||
|
|
BONSAI_TOP_P=0.95
|
||
|
|
BONSAI_TOP_K=20
|
||
|
|
|
||
|
|
# Qwen3.5-9B Abliterated Q4_K_M (standard GGUF; works on Prism llama-server)
|
||
|
|
LLM_ID=qwen9
|
||
|
|
BONSAI_HF_REPO=mradermacher/Qwen3.5-9B-abliterated-v2-MAX-GGUF
|
||
|
|
BONSAI_MAIN_FILE=Qwen3.5-9B-abliterated-v2-MAX.Q4_K_M.gguf
|
||
|
|
BONSAI_MODEL_PATH=/models/Qwen3.5-9B-abliterated-v2-MAX.Q4_K_M.gguf
|
||
|
|
OPENWEBUI_DEFAULT_MODEL=openai/Qwen3.5-9B-abliterated-v2-MAX.Q4_K_M.gguf
|
||
|
|
OPENHANDS_MODEL=openai/Qwen3.5-9B-abliterated-v2-MAX.Q4_K_M.gguf
|
||
|
|
|
||
|
|
DOWNLOAD_MODEL=true
|
||
|
|
DOWNLOAD_QWEN=true
|
||
|
|
DOWNLOAD_BONSAI27=false
|
||
|
|
DOWNLOAD_VISION=false
|