Qwen3.8

Oct 9, 2026

Throughput

210.5 t/s gen · 6708.5 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Use cases

coding

Summary

User reports Qwen3.8 at 210.5 t/s decode and 6708.5 t/s prefill on a single RTX 5090. Setup is NInfer with MTP speculative decoding, 1690 prompt tokens and 3029 generated tokens, 254 ms TTFT. The user runs a demoscene generator where the model writes Three.js effects and revises them from captured video; LM Studio is also supported for the regular workflow.

View source ↗