inclusionAI open-sources vision model Ling-3.0-flash-VL with BF16 and FP8 weights
FellMentKE · x · 2026-09-09
inclusionAI has open-sourced its vision-language model Ling-3.0-flash-VL, with BF16 and FP8 weights now available on Hugging Face and ModelScope; FP4 and INT4 quantizations are coming soon.
- Positioning: beyond visual recognition, the model understands images, video, documents, and UIs, then reasons, searches, verifies, uses tools, checks results, and delivers an outcome — a full visual-to-action loop.
- Demos: with a phone camera it can identify objects, describe scenes aloud, and translate foreign-language signs for travel and accessibility use cases.
- No-code visual editing: it can remove outdated promo elements, replace wrong fonts, or restyle a page based on a reference site.
Developers can download, inspect, and build with the weights today.
More from Models
- Researcher says he predicted Navier-Stokes would fall first, but not amid bitter controversy — geoffreyirving · 2026-09-09
- 'Context-window AGI': inside a single window, models beat any individual — sir_codes_alot · 2026-09-09
- littmath explains why models cracked Navier-Stokes but Riemann is harder — littmath · 2026-09-09
- OpenAI's Internal Model Cracks Open Math Problems Where Humanity Scored Effectively Zero — stevenheidel · 2026-09-09
- GPT-6 Astra Tops Design Arena's 3D Leaderboard With Elo 1495, 65 Pts Ahead of Kimi K3 — airesearch12 · 2026-09-09
- If the NS proof took humans years, internal models may reach decades-long METR horizons — Realistic_Stomach848 · 2026-09-09