qwen2.5-3b-fcgr-lora-gguf : GGUF

• For text only LLMs: llama-cli -hf 4dil/qwen2.5-3b-fcgr-lora-gguf --jinja
• For multimodal models: llama-mtmd-cli -hf 4dil/qwen2.5-3b-fcgr-lora-gguf --jinja

Available Model files:

• Qwen2.5-3B-Instruct.Q5_K_M.gguf
• Qwen2.5-3B-Instruct.Q4_K_M.gguf

Ollama

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