johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot

Qwen3.6-35B-A3B-UD-IQ4_XS fixed for GitHub Copilot

This model package is fixed to work with GitHub Copilot.

It republishes the original GGUF together with the Copilot-compatible Ollama configuration from this repository.

Field	Value
Published repo	johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot
Original model	https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF
GitHub Copilot fix	Included Modelfile with Copilot-safe Ollama tool calling
Weights	Unchanged GGUF weights from the original upstream release
GGUF file	Qwen3.6-35B-A3B-UD-IQ4_XS.gguf
Model Name	qwen36-35b-a3b-ud-iq4xs-128k
Architecture	qwen36
Quantization	UD-IQ4_XS
Context Length	131072

What is included

• Qwen3.6-35B-A3B-UD-IQ4_XS.gguf
• Modelfile
• README.md with release notes and provenance

Use with Ollama

Download the repository contents locally and run:

ollama create my-copilot-model -f Modelfile

The included Modelfile expects ./Qwen3.6-35B-A3B-UD-IQ4_XS.gguf in the same directory.

Provenance

• Generated with ollama-copilot-fixer.

Release Notes

This package keeps the original Unsloth GGUF weights and adds the Ollama Modelfile needed to make the model work cleanly with GitHub Copilot local model agent flows.

Validated in this repo against:

• clean no-think chat output by default
• structured tool calls for Copilot agent turns
• optional think=true reasoning streams on harder prompts

The Copilot-specific fix is in the included Modelfile and runtime settings, not in altered model weights.