Alibaba Qwen Releases Qwen-Image-2.1-Turbo, an 8-Step 7B Image Model
Alibaba’s Qwen team has released Qwen-Image-2.1-Turbo, an accelerated checkpoint of its open-weight Qwen-Image-2.1 model. It generates and edits images in 8 denoising steps instead of the base model’s 40-step default. For developers, that means 5x fewer denoising steps on the same 7B architecture, plus a hosted API option. TL;DR Size: 7B parameters in the visual generator, paired with a Qwen3-VL 8B text encoder. Runs on: CUDA GPUs in BF16 via Diffusers. Qwen publishes no
Get smart on it
Alibaba's Qwen team released an accelerated image generation model called Qwen-Image-2.1-Turbo that generates images in 8 denoising steps instead of the base model's 40 steps, achieving a fivefold reduction in computation. The model maintains the same capabilities as its predecessor, including 2K resolution output and image editing features, while using the same 7B parameter architecture. This matters because faster image generation with lower computational requirements makes the technology more accessible to developers, and the hosted API option costs 2.5 times less per image than the Pro version. However, the weights are research-licensed only, meaning commercial use requires separate permission from the developers.
Related news
TII Releases Falcon-ASR: 1.6B Arabic Speech Model Hits 20.92% WER
The Technology Innovation Institute (TII) in Abu Dhabi has released Falcon-ASR, a 1.6B parameter Arabic speech recognition model. It focuses on the Emirati dialect and also transcribes English, French, Spanish and Portuguese. In TII’s evaluation, Falcon-ASR posts a 20.92% average word error rate (WER) across 6 Arabic test sets. That beats the best published entry in TII’s leaderboard snapshot by 2.25 points. For developers building Arabic voice products, the catch is access: today i
What is Decision 3.0? vLLM Semantic Router’s New Open Decision Models
The vLLM Semantic Router team has released Decision 3.0, a family of multimodal decision models. Decision 3.0 multimodal decision models read text, JSON and images, then answer typed questions about them. There are 5 sizes, from 0.8B to 27B, all under Apache-2.0. For developers, this is a fast way to classify, route and gate requests without parsing generated text. TL;DR Size: 5 models: d3-lite (0.85B), d3-nano (2.21B), d3-mini (4.54B), d3-flash (8.39B), d3 (26.09B). Context length: not
