AI Radar
Support
LiveUpdated 2026-09-19 19:27 UTC

A model that beats GPT on some benchmarks is running on my desk right now. Nobody is…

A model that beats GPT on some benchmarks is running on my desk right now. Nobody is covering it. If you have two…

This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.

A model that beats GPT on some benchmarks is running on my desk right now. Nobody is covering it. If you have two Sparks and you are not checking out Qwen3.8-Flash, you are missing out. Tools at 128k context, the lane where most local models die: 89.7 tok/s, zero XML leakage. Needle 18 for 18 through 900k. Decode within 15% from 8k to 900k. This is one of the best recipes you can run on two Sparks. I ran the full grid on Mia's updated recipe so you do not have to. WHAT IS QWEN 3.8 FLASH Considerable speed, and something the numbers do not capture: Qwen 3.8's humanistic approach. It seem

Posted by Yume_X (2.1k followers) 1 days ago · 5 likes · 1.1k views · view the original post on X. Kept by the AI Radar as Open & local models.

More AI work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.3k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 19:27 UTC. Full method.