FRAMEWIREIndonesiaUpdated Sep 22Live wire
0:00 / 0:00

Qwen 3.8 omni realtime Japanese voice is 🫪

SaltyAomSep 227
0:00 / 0:00

We ran Gemini 3.7 Flash, Gemini 3.8 Flash and self-hosted Qwen3.8-27B through the same grounded video QA pipeline on 300 Perception Test questions.

Gemini wins end to end, Qwen lands at 84% of its HOTA. The biggest lever was not the model at all. Write-up:

Anton SlesarevSep 221
0:00 / 0:00

Qwen 3.8 27b via Tesseract Server

What a phenomenal model that can be run on a Mac

SpokSep 22
0:00 / 0:00

Try out cache-to-cache here

ONE DGX Spark Working with MiaAI_lab recipe of Qwen 3.8 flash next, but you can use any model Simple test of an essay about the research paper:

droveSep 22