Instructions to use userxxx/openhands-qwen-coder-32b-14b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use userxxx/openhands-qwen-coder-32b-14b with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("userxxx/openhands-qwen-coder-32b-14b", dtype="auto")

llama-cpp-python

How to use userxxx/openhands-qwen-coder-32b-14b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="userxxx/openhands-qwen-coder-32b-14b",
	filename="qwencoder32openhands-beta-q4-k-m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use userxxx/openhands-qwen-coder-32b-14b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf userxxx/openhands-qwen-coder-32b-14b
# Run inference directly in the terminal:
llama-cli -hf userxxx/openhands-qwen-coder-32b-14b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf userxxx/openhands-qwen-coder-32b-14b
# Run inference directly in the terminal:
llama-cli -hf userxxx/openhands-qwen-coder-32b-14b

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 userxxx/openhands-qwen-coder-32b-14b
# Run inference directly in the terminal:
./llama-cli -hf userxxx/openhands-qwen-coder-32b-14b

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 userxxx/openhands-qwen-coder-32b-14b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf userxxx/openhands-qwen-coder-32b-14b

Use Docker

docker model run hf.co/userxxx/openhands-qwen-coder-32b-14b

LM Studio
Jan
Ollama
How to use userxxx/openhands-qwen-coder-32b-14b with Ollama:
```
ollama run hf.co/userxxx/openhands-qwen-coder-32b-14b
```

Unsloth Studio new

How to use userxxx/openhands-qwen-coder-32b-14b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for userxxx/openhands-qwen-coder-32b-14b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for userxxx/openhands-qwen-coder-32b-14b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for userxxx/openhands-qwen-coder-32b-14b to start chatting

Pi new

How to use userxxx/openhands-qwen-coder-32b-14b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf userxxx/openhands-qwen-coder-32b-14b

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "userxxx/openhands-qwen-coder-32b-14b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use userxxx/openhands-qwen-coder-32b-14b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf userxxx/openhands-qwen-coder-32b-14b

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 userxxx/openhands-qwen-coder-32b-14b

Run Hermes

hermes

Docker Model Runner
How to use userxxx/openhands-qwen-coder-32b-14b with Docker Model Runner:
```
docker model run hf.co/userxxx/openhands-qwen-coder-32b-14b
```

Lemonade

How to use userxxx/openhands-qwen-coder-32b-14b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull userxxx/openhands-qwen-coder-32b-14b

Run and chat with the model

lemonade run user.openhands-qwen-coder-32b-14b-{{QUANT_TAG}}

List all available models

lemonade list

Summary

The model userxxx/openhands-qwen-coder-32b is a fine-tuned version of qwen2.5-coder-32b, specifically tailored for the Swe Agent OpenHands. It delivers impressive performance, sometimes nearly rivaling that of Sonnet 3.5. However, certain limitations persist, particularly with function calling for IPython/Jupyter commands like INSERT and STR_REPLACE, which currently do not work. Aside from these issues, the model performs effectively in most other tasks.

Recommended Usage

To achieve optimal results, it is recommended to use this model via LM Studio.

Steps to Set Up LM Studio:

Open LM Studio.
Go to the Local Server tab.
Click the "Start Server" button.
Copy qwencoder32openhands-beta-q4-k-m.gguf inside the LmStudio Model Folder and than select it.
Ensure the context window exceeds 4000 tokens

OpenHands Settings

For WSL, run the following commands to set up the networking mode to mirrored:

python -c  "print('[wsl2]\nnetworkingMode=mirrored',file=open(r'%UserProfile%\.wslconfig','w'))"
wsl --shutdown

Setting inside Openhands

openai/lmstudio http://host.docker.internal:1234/v1

Downloads last month: 7

GGUF

Model size

33B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

userxxx
/

openhands-qwen-coder-32b-14b

Summary

Recommended Usage

Steps to Set Up LM Studio:

OpenHands Settings

Dataset used to train userxxx/openhands-qwen-coder-32b-14b