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)