Dflash 2 on M2 Max gave me around 22 tok/s for Qwen 3.8 27B 4Bit from mlx-community
Is this the max I should expect on a M2 Max or the setup required fine tuning? running in oMLX anyone running on M2 Max have similiar results or maybe a bit higher? how good it went for you
You can now build 3D animated websites using Qwen 3.8 27b
Much like the 'build $10k websites using Claude Code', all you need is a solid process and you can achieve similar results Try this out: - Launch Qwen inside - Wire up the higgsfield_ai MCP -
Lip sync AI music video. Fully automatic operation with a system that connects ACE-Step, Krea 2, LTX 2.5, and Qwen 3.8 27B.
Two clips were corrected and recombined. RTX 5090 + DGX Spark
The "tell me without telling me" apocalypse onset
Military grade intervention? In 5-10 years time? It's here now - thx to a reckless "frontier lab push" vs "open weights self-defense-idea" loop - and they don't tell us. Ability to..: 1. ..recursively self-improve 2. ..set
You have reached the end of the archive
All of qwen38