unfd : GGUF

• For text only LLMs: llama-cli -hf richyvd/unfd --jinja
• For multimodal models: llama-mtmd-cli -hf richyvd/unfd --jinja

Available Model files:

• qwen2.5-32b-instruct.Q4_K_M.gguf
• qwen2.5-32b-instruct.BF16-00002-of-00002.gguf

Ollama

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