AnalysisAI ModelsAugust 19, 2026

Dflash2: Qwen3.8-27B hits 138 tps on RTX 3090

A hyper-optimized inference engine for Qwen3.8-27B on an RTX 3090 reaches 138 tokens per second (power-limited to 250W), up from 82 tps single request in the prior release.

1 source

AI Models by email

Get an email when there's news on AI Models

No news that day, no email.

More stories today

Open the live feed
Dflash2: Qwen3.8-27B hits 138 tps on RTX 3090 — AIBriefs