Instructions to use Jahaz/Qwen-Coder-NX-73B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jahaz/Qwen-Coder-NX-73B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Jahaz/Qwen-Coder-NX-73B",
	filename="Qwen-Coder-NX-73B-Iq4kss-00001-of-00134.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Jahaz/Qwen-Coder-NX-73B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Jahaz/Qwen-Coder-NX-73B
# Run inference directly in the terminal:
llama-cli -hf Jahaz/Qwen-Coder-NX-73B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Jahaz/Qwen-Coder-NX-73B
# Run inference directly in the terminal:
llama-cli -hf Jahaz/Qwen-Coder-NX-73B

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 Jahaz/Qwen-Coder-NX-73B
# Run inference directly in the terminal:
./llama-cli -hf Jahaz/Qwen-Coder-NX-73B

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 Jahaz/Qwen-Coder-NX-73B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Jahaz/Qwen-Coder-NX-73B

Use Docker

docker model run hf.co/Jahaz/Qwen-Coder-NX-73B

LM Studio
Jan

vLLM

How to use Jahaz/Qwen-Coder-NX-73B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jahaz/Qwen-Coder-NX-73B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jahaz/Qwen-Coder-NX-73B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jahaz/Qwen-Coder-NX-73B

Ollama
How to use Jahaz/Qwen-Coder-NX-73B with Ollama:
```
ollama run hf.co/Jahaz/Qwen-Coder-NX-73B
```

Unsloth Studio new

How to use Jahaz/Qwen-Coder-NX-73B 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 Jahaz/Qwen-Coder-NX-73B 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 Jahaz/Qwen-Coder-NX-73B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Jahaz/Qwen-Coder-NX-73B to start chatting

Pi new

How to use Jahaz/Qwen-Coder-NX-73B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Jahaz/Qwen-Coder-NX-73B

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": "Qwen-Coder-NX-73B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Jahaz/Qwen-Coder-NX-73B with Docker Model Runner:
```
docker model run hf.co/Jahaz/Qwen-Coder-NX-73B
```

Lemonade

How to use Jahaz/Qwen-Coder-NX-73B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Jahaz/Qwen-Coder-NX-73B

Run and chat with the model

lemonade run user.Qwen-Coder-NX-73B-{{QUANT_TAG}}

List all available models

lemonade list

A Flagship 73B model, like what we remmeber in the past 3 years, lands in MoE.

This model base on Qwen-Coder-Next, which is my fav, was the winner for everything below 397B with my system prompt, till Qwen3.6 27B changed the game.

What can I say? that 27B model is too good, I cannot deny, but look at my poor Arc 770, which seems be abandoned, I decide to continue the journey with my little 'old' Queen,

So here the model is.

For all GPU poor.

Inference: ik_llama.cpp

Thanks:

Qwen Team for bring the base model;

Kimi as assistant;

llama.cpp to make local inference possible;

ik_llama.cpp for SOTA Quants, and faster inference for cpu.

Downloads last month: 1,202

GGUF

Model size

73B params

Architecture

qwen3next

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Jahaz/Qwen-Coder-NX-73B

Base model

Qwen/Qwen3-Coder-Next

Finetuned

(33)

this model