From Hugging Face
- Hub downloads
- 7.8K
- Last update
- 2026-08-09
Qwen3.6-35B-A3B-Escha-W2
A 2-bit quantized version of Qwen3.6-35B-A3B optimized for high performance.
Why it made the shelf
It is a quantized AI model artifact hosted on Hugging Face, serving as a developer tool for running LLMs efficiently.
Seen on
- First seen
- 2 months ago
- Best score
- 3 points · 3 comments
Official signals
What the source shows.
Sourced facts from the places where this tool ships.
Behind the tool
Who built it. How it grew.
People, backing, growth, and ownership. Every claim links to its source.
Official sitehuggingface.co
Source review queued
Public trail
Where it showed up
2 references from 1 publisher.
- First trace
- Hacker News2 months ago
- Strongest thread
- Hacker News3 comments
- 01Hacker NewsStrongest discussion
We quantized Qwen3.6-35B-A3B to 2-bit: 12.3 GB, 225 tok/s on a 4090
- 02
