Instructions to use lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF",
	filename="BF16/Qwen3-Coder-Next-REAP-40B-A3B-BF16-00001-of-00005.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf lovedheart/Qwen3-Coder-Next-REAP-40B-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 lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf lovedheart/Qwen3-Coder-Next-REAP-40B-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 lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL

Use Docker

docker model run hf.co/lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL

LM Studio
Jan
Ollama
How to use lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF with Ollama:
```
ollama run hf.co/lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL
```

Unsloth Studio

How to use lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-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 lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-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 lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF to start chatting

How to use lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL

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": "lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-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 lovedheart/Qwen3-Coder-Next-REAP-40B-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 lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL
```

Lemonade

How to use lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF:Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3-Coder-Next-REAP-40B-A3B-GGUF-Q4_K_XL

List all available models

lemonade list

Information about the dataset is needed

by Blizado - opened Feb 5

Discussion

Blizado

Feb 5

Without any information what dataset was used for REAP this model is useless. REAP use a dataset to find not so much used expert to remove them and keep others. If for example the dataset has only python code a REAP model would be only work good for python. Without any information about the dataset no one who is interested in this model knows for what coding language this REAP model is useful (and for what not) and since this is a 50% REAP this information is even more important.

Blizado changed discussion title from Dataset is needed to Information about the dataset is needed Feb 5

spanspek

Feb 7

Agreed, so far a few people have tried to create REAPs but from what I can tell the only team to really pull it off successfully is Cerebras (the inventors of REAP)

rahul7star

Feb 12

How these conversions are done?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment