inclusionAI open-sources Ling-3.0-flash-VL: 124B total/5.5B active, 1M context, MIT licensed
AdinaYakup · x · 2026-09-09
inclusionAI released the open-source vision-language model Ling-3.0-flash-VL, now on Hugging Face:
- Native image and video input, built around an understand → reason → act → verify loop
- 124B total parameters with only 5.5B active (MoE), 1M token context
- MIT licensed, fully open for commercial use
An aggressive open-source spec combination for video understanding and long-context multimodal applications.
More from Models
- OpenAI ships GPT-6.1 Terra: +15 points on Agents' Last Exam at roughly 1/3 the cost — reach_vb · 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
- GPT-6.1 Terra cuts hallucination rate by 50 points while lifting accuracy 2 points — ArtificialAnlys · 2026-10-27
- OpenAI's GPT-6.1 Terra matches more intelligence at under a third the cost of GPT-5.6 Terra — ArtificialAnlys · 2026-10-27
- Leaked Terminal-Bench 4.0 chart shows GPT-6.1 Terra leading at lowest cost, unverified — Angaisb_ · 2026-10-27
- OpenAI brings GPT-6.1 Terra to the API and Codex for fast, cheap computer use — OpenAIDevs · 2026-10-27