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- No-code visual editing: it can remove outdated promo elements, replace wrong fonts, or restyle a page based on a reference site.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
- GPT-6.1 Terra lands: early users praise speed, value and subagent performance — BenBajarin · 2026-10-27
- Leaked GPT-6.1 Terra benchmarks: cheap but 'boring', still far behind Astra and Claude — Angaisb_ · 2026-10-27
- Artificial Analysis breaks down all sub-evaluations in Intelligence Index v4.3.2 — ArtificialAnlys · 2026-10-27
- GPT-6.1 Terra gains ~20 points on Terminal-Bench 4.0, rivalling GPT-6.1 Sol — ArtificialAnlys · 2026-10-27
- GPT-6.1 Terra cuts hallucination rate by 50 points while lifting accuracy 2 points — ArtificialAnlys · 2026-10-27
- GPT-6.1 Terra scores 48 on AA Coding Agent Index at one-third the cost of GPT-5.6 Terra — ArtificialAnlys · 2026-10-27