You can deploy this model and start earning money today!

Abdul889/
Qwen2.5-3B-Instruct-GGUF

Name: Qwen2.5-3B-Instruct-GGUF
Availability: InStock

Views

No views yet

Qwen2.5-3B-Instruct-GGUF

This repository contains a fine-tuned version of Qwen2.5-3B-Instruct converted to GGUF format for local inference.

The model was fine-tuned on a small, focused support-style dataset to answer technical questions in a clear, helpful, and conversational way.

Available GGUF files:

Also included:

llama-cli -hf Abdul889/Qwen2.5-3B-Instruct-GGUF --jinja

bash

ollama create qwen2-5-3b-support -f Modelfile
ollama run qwen2-5-3b-support

This model is intended for local use and experimentation.
Q4_K_M is recommended for most users.
F16 is recommended if you want the highest fidelity output and have enough memory.

This model was fine-tuned using supervised fine-tuning and then converted with Unsloth into GGUF format.