Instructions to use toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx"

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 toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx

Run Hermes

hermes

OpenClaw new

How to use toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx"

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 "toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx

This model was converted to MLX 4-bit format from lovedheart/Qwen3-Coder-Next-REAP-48B-A3B-GGUF using mlx-lm version 0.30.6.

Model Specifications

Type: Causal Language Models
Number of Parameters: 48B in total and 3B activated
Number of Layers: 48
Context Length: 262,144 natively and extensible up to 1,010,000 tokens
Compression Method: REAP (Router-weighted Expert Activation Pruning)
Compression Ratio: 40% expert pruning
Quantization: 4-bit, group size 64

Recommended Inference Settings

Parameter	Value
Temperature	1.0
Top-K	40
Top-P	0.95
Min-P	0.01
KV Cache Quantization	Off

Performance

Hardware	Memory	Speed
Mac Mini M4 Pro	64GB	60+ tokens/s

Acknowledgements

Thanks to lovedheart for providing the original model.

Usage

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("lovedheart/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx")
response = generate(model, tokenizer, prompt="Hello, who are you?", max_tokens=512)
print(response)

Downloads last month: 842

Safetensors

Model size

49B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for toby1991/Qwen3-Coder-Next-REAP-48B-A3B-4bit-mlx

Base model

Qwen/Qwen3-Coder-Next

Quantized

(111)

this model