---
language: en
license: other
tags:
- gguf
- qwen2
- text-generation
pipeline_tag: text-generation
base_model: Qwen/Qwen2.5-3B-Instruct
---

# lama_creo_mlx_gguf

GGUF export of the fused local Qwen2.5 3B project model.

## Files

- `qwen25-3b-project-fused-f16.gguf` — F16 GGUF converted from the fused/dequantized MLX model.