Alibaba's Qwen3.8-Max Released, TokenSpeed Announces Inference Optimization

zhyncs42 · x · 2026-08-03

Alibaba's Qwen team has officially released Qwen3.8-Max, claiming it sets a new bar for coding and cowork.

Simultaneously, inference provider TokenSpeed announced Day-0 support for the model. They are currently optimizing multi-node inference to improve per-GPU TPM at high per-user TPS.

Related event: Alibaba Releases 2.4T Parameter Qwen3.8-Max, Open Weights Next Week(13 posts)→

Original post →

More from Infra

Infra channel →