Industry
WAIT WHAT?! 2-bit Qwen3.6-35B-A3B is lightning fast and it only needs 13 GB RAM. “did a complete repo bug hunt with evidence, repro, fixes, …
A developer successfully optimized Qwen 3.6-35B model to 2-bit quantization, achieving significant performance improvements with only 13GB RAM requirements while maintaining functionality. The work in
A developer successfully optimized Qwen 3.6-35B model to 2-bit quantization, achieving significant performance improvements with only 13GB RAM requirements while maintaining functionality. The work included comprehensive debugging of repository issues with documented evidence, reproduction steps, and implemented fixes for the quantization process.
Related
- Boom, the game is changed GLM 5.1 running locally seems to actually work… Now I can run a lot of my @openclaw workflows for the cost of elec…
- DFlash for Kimi-K2.5 was pushed 3 hours ago! Acceptance length varies from 4.0 to 6.3 on datasets. This is only with SGLang btw. https://hug…
- We're delighted to announce that MiniMax M2.7 is now officially open source. With SOTA performance in SWE-Pro (56.22%) and Terminal Bench 2 …
- The most powerful LLM to run at home:
Source: Clem Delangue (X) | 2026-04-16