phi-4-mini-reasoning-finetuned-150-steps : GGUF

• For text only LLMs: llama-cli -hf nex1ff/phi-4-mini-reasoning-finetuned-150-steps --jinja
• For multimodal models: llama-mtmd-cli -hf nex1ff/phi-4-mini-reasoning-finetuned-150-steps --jinja

Available Model files:

• phi-4-mini-reasoning.BF16.gguf

Ollama

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