Post by Jun Song on X
Jun Song@jun_song
XMaybe 5,000tps Qwen3.8-27b personal AMD hardware box is coming soon.
Taalas runs Llama 3.1 8b with 17,000tok/s
It etches the model weight directly on ASIC.
Can't wait to see this magic with Qwen or Gemini.
416 likes39 repliesPosted Aug 7, 2026