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

Libraries

How to use mudler/Qwen3-Coder-Next-APEX-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mudler/Qwen3-Coder-Next-APEX-GGUF",
	filename="Qwen3-Coder-Next-APEX-Balanced.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 mudler/Qwen3-Coder-Next-APEX-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mudler/Qwen3-Coder-Next-APEX-GGUF
# Run inference directly in the terminal:
llama-cli -hf mudler/Qwen3-Coder-Next-APEX-GGUF

Install from WinGet (Windows)

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

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 mudler/Qwen3-Coder-Next-APEX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf mudler/Qwen3-Coder-Next-APEX-GGUF

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 mudler/Qwen3-Coder-Next-APEX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mudler/Qwen3-Coder-Next-APEX-GGUF

Use Docker

docker model run hf.co/mudler/Qwen3-Coder-Next-APEX-GGUF

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

Unsloth Studio new

How to use mudler/Qwen3-Coder-Next-APEX-GGUF 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 mudler/Qwen3-Coder-Next-APEX-GGUF 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 mudler/Qwen3-Coder-Next-APEX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

How to use mudler/Qwen3-Coder-Next-APEX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mudler/Qwen3-Coder-Next-APEX-GGUF

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": "mudler/Qwen3-Coder-Next-APEX-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mudler/Qwen3-Coder-Next-APEX-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mudler/Qwen3-Coder-Next-APEX-GGUF

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 mudler/Qwen3-Coder-Next-APEX-GGUF

Run Hermes

hermes

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

Lemonade

How to use mudler/Qwen3-Coder-Next-APEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mudler/Qwen3-Coder-Next-APEX-GGUF

Run and chat with the model

lemonade run user.Qwen3-Coder-Next-APEX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

⚡ Each donation = another big MoE quantized

I host 25+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory) — enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant.
If APEX quants are useful to you, your support directly funds those bigger runs.

🎉 Patreon (Monthly) | ☕ Buy Me a Coffee | ⭐ GitHub Sponsors

💚 Big thanks to Hugging Face for generously donating additional storage — much appreciated.

Qwen3-Coder-Next APEX GGUF

APEX (Adaptive Precision for EXpert Models) quantizations of Qwen3-Coder-Next.

Brought to you by the LocalAI team | APEX Project | Technical Report

Benchmark Results

Benchmarks coming soon. For reference APEX benchmarks on the Qwen3.5-35B-A3B architecture, see mudler/Qwen3.5-35B-A3B-APEX-GGUF.

What is APEX?

APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient -- edge layers get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).

See the APEX project for full details, technical report, and scripts.

Architecture

Model: Qwen3-Coder-Next (Qwen3Next)
Layers: 48
Experts: 512 routed + shared (10 active per token)
Total Parameters: ~80B
Active Parameters: ~8-10B per token
Attention: Hybrid (standard every 4th layer + linear attention)
Context: 262K tokens
APEX Config: 5+5 symmetric edge gradient across 48 layers
Calibration: v1.3 diverse dataset (chat, code, reasoning, multilingual, tool-calling, Wikipedia)

Run with LocalAI

local-ai run mudler/Qwen3-Coder-Next-APEX-GGUF@Qwen3-Coder-Next-APEX-I-Balanced.gguf

Credits

APEX is brought to you by the LocalAI team. Developed through human-driven, AI-assisted research. Built on llama.cpp.

Downloads last month: 7,256

GGUF

Model size

80B params

Architecture

qwen3next

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 mudler/Qwen3-Coder-Next-APEX-GGUF

Base model

Qwen/Qwen3-Coder-Next

Quantized

(101)

this model

Collection including mudler/Qwen3-Coder-Next-APEX-GGUF

APEX Quants (GGUF)

Collection

MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 34 items • Updated 2 days ago • 96