Instructions to use johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS
# Run inference directly in the terminal:
llama cli -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS
# Run inference directly in the terminal:
llama cli -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS

Use Docker

docker model run hf.co/johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS

LM Studio
Jan
Ollama
How to use johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot with Ollama:
```
ollama run hf.co/johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS
```
Unsloth Desktop

How to use johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot with Docker Model Runner:
```
docker model run hf.co/johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS
```

Lemonade

How to use johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS

Run and chat with the model

lemonade run user.qwen36-35b-a3b-ud-iq4xs-128k-github-copilot-UD-IQ4_XS

List all available models

lemonade list

Hermes Agent

How to use johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "johnml1135/qwen36-35b-a3b-ud-iq4xs-128k-github-copilot:UD-IQ4_XS" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

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.

Downloads last month: 107

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

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

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

unsloth/Qwen3.6-35B-A3B-GGUF

Quantized

(4)

this model