Bottom line! It’s hard to build a company and have big IPO’s when open weight models provide IP security and a less expensive solution.
Grok rank Qwen 3.8 vs common cloud models.
One AI model now watches and listens to your whole video
Qwen 3.8 Omni Flash turns it into a recap without chopping anything up.
Here's an example of Jev routing tools, skills, cli commands for Qwen 3.8 27B on cerebras to format a Power BI report.
Changes are almost instant; working on Linux, only wait due to publishing and refreshing embedded report. The video is not sped up, at all. Just a start.
Ran Qwen 3.8 Flash Next on a MacBook M5, 24GB: thinking off, 2K context, ~4 tokens/sec.
Users say it's practically unusable on this laptop, especially prefilling, bump context up and it takes hours. 24GB just isn't enough for a model this size, even quantized.
You have reached the end of the archive
All of qwen38