← Back to feed

I pushed Qwen3.8-27B to 99 tps on a single request and 1150 on batch on a 3090

AI · Technology · 2026-08-17 12:05:00

Achieved 99 tps on single requests and 1150 on batch for Qwen3.8-27B on RTX 3090.

Source: github.com

Auto-generated summary for reference only. RSS