Qwen3-4B-Thinking-4-gguf : GGUF

• For text only LLMs: llama-cli -hf uberkie/Qwen3-4B-Thinking-4-gguf --jinja
• For multimodal models: llama-mtmd-cli -hf uberkie/Qwen3-4B-Thinking-4-gguf --jinja

Available Model files:

• qwen3-4B.Q4_K_M.gguf This was trained 2x faster with Unsloth