Qwen2.5-3B-Makisu-V2.0.1-GGUF : GGUF

• For text only LLMs: ./llama.cpp/llama-cli -hf RinKana/Qwen2.5-3B-Makisu-V2.0.1-GGUF --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf RinKana/Qwen2.5-3B-Makisu-V2.0.1-GGUF --jinja

Available Model files:

• qwen3-4b-thinking-2507.Q4_K_M.gguf

Ollama

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