Instructions to use rakmik/Qwen3-235B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use rakmik/Qwen3-235B 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 rakmik/Qwen3-235B
# Run inference directly in the terminal:
llama cli -hf rakmik/Qwen3-235B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rakmik/Qwen3-235B
# Run inference directly in the terminal:
llama cli -hf rakmik/Qwen3-235B

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 rakmik/Qwen3-235B
# Run inference directly in the terminal:
./llama-cli -hf rakmik/Qwen3-235B

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 rakmik/Qwen3-235B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rakmik/Qwen3-235B

Use Docker

docker model run hf.co/rakmik/Qwen3-235B

LM Studio
Jan
Ollama
How to use rakmik/Qwen3-235B with Ollama:
```
ollama run hf.co/rakmik/Qwen3-235B
```

Unsloth Studio

How to use rakmik/Qwen3-235B 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 rakmik/Qwen3-235B 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 rakmik/Qwen3-235B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rakmik/Qwen3-235B to start chatting

How to use rakmik/Qwen3-235B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rakmik/Qwen3-235B

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": "rakmik/Qwen3-235B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use rakmik/Qwen3-235B with Docker Model Runner:
```
docker model run hf.co/rakmik/Qwen3-235B
```

Lemonade

How to use rakmik/Qwen3-235B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rakmik/Qwen3-235B

Run and chat with the model

lemonade run user.Qwen3-235B-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use rakmik/Qwen3-235B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rakmik/Qwen3-235B

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 rakmik/Qwen3-235B

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use rakmik/Qwen3-235B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rakmik/Qwen3-235B

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 "rakmik/Qwen3-235B" \
  --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"

from

unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF

split Qwen3-235B-A22B-Instruct-2507-GGUF/Q2_K

to 9 parts part=10gb

Downloads last month: 22

GGUF

Model size

235B params

Architecture

qwen3moe

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

Model tree for rakmik/Qwen3-235B

Base model

Qwen/Qwen3-235B-A22B-Instruct-2507

Quantized

unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF

Quantized

(1)

this model