Qwen3-Coder-Next-REAP-48B-A3B-GGUF

Instructions to use Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF 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 Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL

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 Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL

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 Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL

Use Docker

docker model run hf.co/Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL

LM Studio
Jan
Ollama
How to use Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF with Ollama:
```
ollama run hf.co/Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL
```
Unsloth Desktop

How to use Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL
```

Lemonade

How to use Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3-Coder-Next-REAP-48B-A3B-GGUF-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL

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 Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL

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 "Ai2-Alliance/Qwen3-Coder-Next-REAP-48B-A3B-GGUF:Q4_K_XL" \
  --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"

Qwen3-Coder-Next-REAP-48B-A3B-GGUF / README.md

Ai2-Alliance

Duplicate from lovedheart/Qwen3-Coder-Next-REAP-48B-A3B-GGUF

239b520 7 months ago

preview code

Raw

History Blame Contribute Delete

2.1 kB

	---
	base_model:
	- Qwen/Qwen3-Coder-Next
	tags:
	- text-generation-inference
	license: apache-2.0
	---



	![Qwen3-coder-next-reap](https://cdn-uploads.huggingface.co/production/uploads/68121d80da035a609e569a81/PUEUf6Zz1JToRJfgI7HMk.png)


	Qwen3-Coder-Next-REAP-48B-A3B has the following specifications:

	- Type: Causal Language Models
	- Number of Parameters: 48B in total and 3B activated
	- Hidden Dimension: 2048
	- Number of Layers: 48
	- Hybrid Layout: 12 * (3 * (Gated DeltaNet -> MoE) -> 1 * (Gated Attention -> MoE))
	- Gated Attention:
	- Number of Attention Heads: 16 for Q and 2 for KV
	- Head Dimension: 256
	- Rotary Position Embedding Dimension: 64
	- Gated DeltaNet:
	**Number of Linear Attention Heads: 32 for V and 16 for QK
	**Head Dimension: 128
	- Mixture of Experts:
	- **Number of Experts: 308 (uniformly pruned from 512)
	- **Number of Activated Experts: 10
	- **Number of Shared Experts: 1
	- Context Length: 262,144 natively
	- Compression Method: REAP (Router-weighted Expert Activation Pruning)
	- Compression Ratio: 40% expert pruning

	Test video 1 (agentic task) @Q4_K_XL : https://www.bilibili.com/video/BV1f8cNzcEHV/
	Prompt: please clone the repository https://github.com/ggml-org/llama.cpp in /home/lovedheart/llama_ and review the PR 19435.

	Test video 2 -> fastllm (int8 quantization) approx. Q8_0 in GGUF : https://www.bilibili.com/video/BV1hwFJzXEVP/
	Prompt: Create a cosmic nebula background using Three.js with the following requirements: a deep black space background with twinkling white stars; 2–3 large semi-transparent purple/pink nebula clouds with a smoky texture; slow rotation animation; optimized for white text display. Implementation details: 1. Starfield: 5000 white particles randomly distributed with subtle twinkling; 2. Nebula: 2–3 large purple particle clusters using additive blending mode; 3. Colors: #8B5CF6, #C084FC, #F472B6 (purple to pink gradient); 4. Animation: overall rotation.y += 0.001, stars' opacity flickering; 5. Setup: WebGLRenderer with alpha:true and black background.