Qwen3-Coder-REAP-25B-A3B-qx65x-hi-mlx

360
1
25.0B
2 languages
license:apache-2.0
by
nightmedia
Language Model
OTHER
25B params
New
360 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
56GB+ RAM
Mobile
Laptop
Server
Quick Summary

This version of the Deckard(qx) formula uses embeddings at 6 bit, along with the head and select attention paths, leaving the rest at 5 bit.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
24GB+ RAM

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.