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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lovedheart/Qwen3-Next-REAP-40B-A3B-Instruct-GGUF",
	filename="BF16/Qwen3-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-Next-REAP-40B-A3B-Instruct-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-Next-REAP-40B-A3B-Instruct-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf lovedheart/Qwen3-Next-REAP-40B-A3B-Instruct-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-Next-REAP-40B-A3B-Instruct-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf lovedheart/Qwen3-Next-REAP-40B-A3B-Instruct-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-Next-REAP-40B-A3B-Instruct-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf lovedheart/Qwen3-Next-REAP-40B-A3B-Instruct-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-Next-REAP-40B-A3B-Instruct-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lovedheart/Qwen3-Next-REAP-40B-A3B-Instruct-GGUF:Q4_K_XL

Use Docker

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

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

Unsloth Studio

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

How to use lovedheart/Qwen3-Next-REAP-40B-A3B-Instruct-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-Next-REAP-40B-A3B-Instruct-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-Next-REAP-40B-A3B-Instruct-GGUF:Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

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

Run Hermes

hermes

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

lovedheart commited on Jan 25

Commit

c0d40da

verified ·

1 Parent(s): 1f5780e

Create README.md

Browse files

Files changed (1) hide show

README.md +33 -0

README.md ADDED Viewed

	@@ -0,0 +1,33 @@

+---
+base_model:
+- Qwen/Qwen3-Next-80B-A3B-Instruct
+tags:
+- text-generation-inference
+license: apache-2.0
+---
+![qwen3-next-instruction](https://cdn-uploads.huggingface.co/production/uploads/68121d80da035a609e569a81/Ft9cmZlll_PehtFYkESxH.png)
+**Qwen3-Next-REAP-40B-A3B-Instruct** has the following specifications:
+- **Type:** Causal Language Models
+- **Number of Parameters**: 40B 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: 256 (uniformly pruned from 512)
+- **Number of Activated Experts: 10
+- **Number of Shared Experts: 1
+- **Context Length**: 262,144 natively and extensible up to 1,010,000 tokens
+- **Compression Method**: REAP (Router-weighted Expert Activation Pruning)
+- **Compression Ratio**: 50% expert pruning