Downloads · 30 days
276
19% of all-time downloads
qwen36-35b-a3b-ud-iq4xs-128k-github-copilot
johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot
qwen36-35b-a3b-ud-iq4xs-128k-github-copilot is a machine learning model from johnml1135. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model package is fixed to work with GitHub Copilot.
All-time downloads
1.5K
Public
Repo size
17.7 GB
Likes
6
Trending 1
Repo makeup
Click a slice to open those files.
.gguf17.7 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Apr 17, 2026
- Updated
- Apr 17, 2026
- SHA
- 151e7552
Base models
Model card
From the Hugging Face model README
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.ggufModelfileREADME.mdwith 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=truereasoning streams on harder prompts
The Copilot-specific fix is in the included Modelfile and runtime settings, not in altered model weights.
- License
- apache-2.0
- Created
- Apr 17, 2026
- Updated
- Apr 17, 2026