tomasz-syn-grzegorza
359afb3a59
Infrastructure configs for GMKtec K11 (Docker, vLLM, LocalAI, ComfyUI, control-plane, gpu-fan agent, Server UI with CLI/file explorer/GPU fan curve). Co-authored-by: Cursor <cursoragent@cursor.com>
33 lines
1.3 KiB
YAML
33 lines
1.3 KiB
YAML
# Model catalog — no automatic download on stack install.
|
|
# Use: ./scripts/list-models.sh
|
|
# ./scripts/download-model.sh <id>
|
|
|
|
models:
|
|
- id: qwen3.6-27b-q4-gguf
|
|
name: Qwen3.6-27B Q4_K_M
|
|
runtime: llamacpp
|
|
hf_repo: lmstudio-community/Qwen3.6-27B-GGUF
|
|
gguf_file: Qwen3.6-27B-Q4_K_M.gguf
|
|
download_url: https://huggingface.co/lmstudio-community/Qwen3.6-27B-GGUF/resolve/main/Qwen3.6-27B-Q4_K_M.gguf
|
|
size_gb: 17
|
|
local_path: /data/apps/gguf/qwen3.6-27b/Qwen3.6-27B-Q4_K_M.gguf
|
|
|
|
- id: gemma-4-12b-q4-gguf
|
|
name: Gemma 4 12B Q4_0
|
|
runtime: llamacpp
|
|
hf_repo: lmstudio-community/gemma-4-12B-it-QAT-GGUF
|
|
gguf_file: gemma-4-12B-it-QAT-Q4_0.gguf
|
|
mmproj_file: mmproj-gemma-4-12B-it-QAT-BF16.gguf
|
|
download_url: https://huggingface.co/lmstudio-community/gemma-4-12B-it-QAT-GGUF/resolve/main/gemma-4-12B-it-QAT-Q4_0.gguf
|
|
mmproj_url: https://huggingface.co/lmstudio-community/gemma-4-12B-it-QAT-GGUF/resolve/main/mmproj-gemma-4-12B-it-QAT-BF16.gguf
|
|
size_gb: 7
|
|
local_dir: /data/apps/gguf/gemma-4-12b
|
|
|
|
- id: qwen3.6-27b-awq-vllm
|
|
name: Qwen3.6-27B AWQ (vLLM interim)
|
|
runtime: vllm
|
|
hf_model: Qwen/Qwen3.6-27B-Instruct-AWQ
|
|
profile: qwen3.6-27b-awq-128k
|
|
size_gb: 15
|
|
note: AWQ on vLLM — Q4 equivalent until llama.cpp stack is ready
|