qwen_base_finetune : GGUF

• For text only LLMs: llama-cli -hf pphan720/qwen_base_finetune --jinja
• For multimodal models: llama-mtmd-cli -hf pphan720/qwen_base_finetune --jinja

Available Model files:

• qwen3-4b-base.Q5_K_M.gguf
• qwen3-4b-base.Q8_0.gguf
• qwen3-4b-base.Q4_K_M.gguf This was trained 2x faster with Unsloth