qwen_finetune : GGUF

• For text only LLMs: ./llama.cpp/llama-cli -hf hussamzahrani/qwen_finetune --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf hussamzahrani/qwen_finetune --jinja

Available Model files:

• qwen3-vl-8b-instruct.Q4_K_M.gguf
• qwen3-vl-8b-instruct.BF16-mmproj.gguf This was trained 2x faster with Unsloth