Instructions to use edwardyoon79/Qwen3-Coder-Next-TQ3_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use edwardyoon79/Qwen3-Coder-Next-TQ3_0 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 edwardyoon79/Qwen3-Coder-Next-TQ3_0
# Run inference directly in the terminal:
llama cli -hf edwardyoon79/Qwen3-Coder-Next-TQ3_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf edwardyoon79/Qwen3-Coder-Next-TQ3_0
# Run inference directly in the terminal:
llama cli -hf edwardyoon79/Qwen3-Coder-Next-TQ3_0

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 edwardyoon79/Qwen3-Coder-Next-TQ3_0
# Run inference directly in the terminal:
./llama-cli -hf edwardyoon79/Qwen3-Coder-Next-TQ3_0

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 edwardyoon79/Qwen3-Coder-Next-TQ3_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf edwardyoon79/Qwen3-Coder-Next-TQ3_0

Use Docker

docker model run hf.co/edwardyoon79/Qwen3-Coder-Next-TQ3_0

LM Studio
Jan
Ollama
How to use edwardyoon79/Qwen3-Coder-Next-TQ3_0 with Ollama:
```
ollama run hf.co/edwardyoon79/Qwen3-Coder-Next-TQ3_0
```

Unsloth Studio

How to use edwardyoon79/Qwen3-Coder-Next-TQ3_0 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 edwardyoon79/Qwen3-Coder-Next-TQ3_0 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 edwardyoon79/Qwen3-Coder-Next-TQ3_0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for edwardyoon79/Qwen3-Coder-Next-TQ3_0 to start chatting

How to use edwardyoon79/Qwen3-Coder-Next-TQ3_0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf edwardyoon79/Qwen3-Coder-Next-TQ3_0

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": "edwardyoon79/Qwen3-Coder-Next-TQ3_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use edwardyoon79/Qwen3-Coder-Next-TQ3_0 with Docker Model Runner:
```
docker model run hf.co/edwardyoon79/Qwen3-Coder-Next-TQ3_0
```

Lemonade

How to use edwardyoon79/Qwen3-Coder-Next-TQ3_0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull edwardyoon79/Qwen3-Coder-Next-TQ3_0

Run and chat with the model

lemonade run user.Qwen3-Coder-Next-TQ3_0-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use edwardyoon79/Qwen3-Coder-Next-TQ3_0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf edwardyoon79/Qwen3-Coder-Next-TQ3_0

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 edwardyoon79/Qwen3-Coder-Next-TQ3_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use edwardyoon79/Qwen3-Coder-Next-TQ3_0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf edwardyoon79/Qwen3-Coder-Next-TQ3_0

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 "edwardyoon79/Qwen3-Coder-Next-TQ3_0" \
  --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"

edwardyoon79 commited on Mar 28

Commit

928ea48

verified ·

1 Parent(s): f993d9c

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -16,18 +16,18 @@ tags:
 This repository contains the TQ3_0 quantized version of the `Qwen3-Coder-Next` model, specifically optimized for the latest NVIDIA hardware.
 ## 🚀 Model Highlights
-- **Quantization Method**: **TurboQuant (TQ3_0)** - **Hardware Used**: Quantized on a dedicated **NVIDIA GeForce RTX 5090**.
 - **Optimization**: Built using a custom-patched `llama.cpp` (llama-turbo) to support the high-efficiency TQ3_0 algorithm.
-- **Performance**: Designed for ultra-fast inference and low VRAM usage while maintaining high coding intelligence.
 ## 🛠️ Quantization Details
-The **TQ3_0** format utilizes advanced Lloyd-Max quantization and Walsh-Hadamard Transform (WHT) to minimize information loss during 3-bit compression. This model provides a perfect balance between speed and intelligence for developers.
-- **BPW (Bits Per Weight)**: ~3.0
-- **Size**: Approximately 30-35 GB (optimized for 32GB+ VRAM GPUs)
 ## 💻 How to Use
 To run this model, you need a compatible inference engine that supports TurboQuant.

 This repository contains the TQ3_0 quantized version of the `Qwen3-Coder-Next` model, specifically optimized for the latest NVIDIA hardware.
 ## 🚀 Model Highlights
+- **Quantization Method**: **TurboQuant (TQ3_0)** — Fine-tuned for superior intelligence retention.
+- **Target Bitrate**: **3.25 bpw** (Bits Per Weight) — Strategic sweet spot between 3-bit and 4-bit quantization.
+- **Hardware Used**: Quantized on a dedicated **NVIDIA GeForce RTX 5090**.
 - **Optimization**: Built using a custom-patched `llama.cpp` (llama-turbo) to support the high-efficiency TQ3_0 algorithm.
 ## 🛠️ Quantization Details
+The **TQ3_0** format utilizes advanced Lloyd-Max quantization and Walsh-Hadamard Transform (WHT) to minimize information loss. This specific version has been calibrated to **3.25 bpw**, offering a balanced sweet spot between 3-bit and 4-bit quantization.
+- **BPW (Bits Per Weight)**: 3.25
+- **Size**: Approximately **30.4 GB** (ideally suited for 32GB VRAM GPUs like the RTX 5090)
+- **Efficiency**: Balanced for ultra-fast throughput while maintaining high-level coding logic.
 ## 💻 How to Use
 To run this model, you need a compatible inference engine that supports TurboQuant.