AI Radar
Support
LiveUpdated 2026-09-19 20:46 UTC

A single RTX 3090 hit 381 tok/s on Qwen3.8-27B.

A single RTX 3090 hit 381 tok/s on Qwen3.8-27B. DFlash2 + lookup: 138 Optimized MTP: 114 context lookup so the model…

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

A single RTX 3090 hit 381 tok/s on Qwen3.8-27B. DFlash2 + lookup: 138 Optimized MTP: 114 context lookup so the model verifies 16 tokens at once when the answer already lives in the prompt. Longer verification & prefix cache: 381 tok/s The 381 number only appears when the model is reproducing or extracting from a long prompt. That’s the point. Prefix cache also drops TTFT from 22s to 0.56s on the second question against the same document. Best for RAG, document Q&A, and coding agents. Regular chat still lands around 133 tok/s. 25K-token context. https://x.com/TeksEdge/status/209059599011

Posted by Md Ismail Šojal 🕷️ (55.6k followers) 1 h ago · 14 likes · 1.2k views · view the original post on X. Kept by the AI Radar as AI infra & evals.

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. 31.3k posts from 4.7k X accounts over the last 14 days, 1.3k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 20:46 UTC. Full method.