Qwen-Image 2.1 local test: transparency, text and infographics at 30.8GB
DevDminGod · x · 2026-09-20
Hands-on with Qwen-Image 2.1 running locally: pretty images, transparency support, coherent text rendering, dense infographics (though below NBP and GPT), up to 10 input images, precise selective editing, and chaining images into simple "animated" videos.
- 30.84 GiB on disk: 16.33 GiB text encoder + 13.25 GiB image transformer + 1.26 GiB VAE
- Runs on a 48GB M5 Mac using 31GB while generating, despite no Mac-specific optimization yet
The author calls it a very strong open-weights release.
More from Multimodal
- Izwi: open-source offline voice cloning in Rust, runs on 16GB M1 Pro — zinyando · 2026-11-12
- MiniMax H3 Image generates 3D game scenes in 10s, over 3x faster than GPT Image — HeyToha · 2026-11-12
- Dev releases local world model turning any image into interactive video, runs on RTX 3060 — lucidml_lover · 2026-11-12
- Ex-Meta CV researcher builds AdaL v2, a chat-driven video agent harness for GTM — Scobleizer · 2026-11-12
- MiniMax H3 image gen runs locally on AMD RX 9070, 25-30s per 4MP image — omglionheaded · 2026-11-12
- One reference, one prompt, three image models: side-by-side Nano Banana Pro vs GPT Image 2.6 test — gizakdag · 2026-11-12