mikecovlee/qwen3.8-27b-24gb-recipe
Run Qwen3.8-27B locally on any 24GB GPU (RTX 3090/4090/A5000) with llama.cpp: install, scripts, MTP tuning, benchmarks
正在读取项目信息…
Run Qwen3.8-27B locally on any 24GB GPU (RTX 3090/4090/A5000) with llama.cpp: install, scripts, MTP tuning, benchmarks