Qwen-Image 2.1 open weights land with day-0 SGLang support, runs on one RTX 4090

ying11231 · x · 2026-09-21

Alibaba's Qwen team released open-weight Qwen-Image-2.1, a 7B unified generation/editing model with native RGBA transparency and up to 10 reference images. SGLang shipped day-0 support: native precision on a single RTX 4090 24GB with CPU offload (18.7s for 1024×1024, 21.7s editing, 22.7 GiB peak), 8.0s/9.6s on RTX PRO 6000, with TP/SP, LoRA and OpenAI-compatible APIs at 40 denoising steps, no quantization.

Related event: Alibaba open-sources Qwen-Image-2.1, a 7B unified image generation and editing model(27 posts)→

Original post →

More from Infra

Infra channel →