ComPilar-Qwen3-4b : GGUF

• For text only LLMs: ./llama.cpp/llama-cli -hf metacogna/ComPilar-Qwen3-4b --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf metacogna/ComPilar-Qwen3-4b --jinja

Available Model files:

• qwen3-4b-instruct-2507.Q5_K_M.gguf
• qwen3-4b-instruct-2507.Q8_0.gguf
• qwen3-4b-instruct-2507.Q4_K_M.gguf

Ollama

An Ollama Modelfile is included for easy deployment. This was trained 2x faster with Unsloth