BirdToast/qwen3.5-9b-fujin-gguf

Qwen3.5-9B Fujin v2 — GGUF Q8_0

GGUF Q8_0 quantization of BirdToast/qwen3.5-9b-fujin.

Details

• Base model: Qwen/Qwen3.5-9B
• Fine-tune: LoRA SFT (r=32, alpha=64) merged to base
• Quantization: Q8_0 (~8.9GB)
• Format: GGUF (compatible with llama.cpp, ollama, etc.)

Usage

# llama.cpp
./llama-server -m qwen3.5-9b-fujin-v2-Q8_0.gguf -ngl 99 --ctx-size 4096

See the full model card at BirdToast/qwen3.5-9b-fujin for training details.