DotSight AI Releases Open-Source 280B Multimodal Model with Apache 2.0 License
Xianbao_QIAN · x · 2026-08-14
DotSight AI has released a new open-source model under the Apache 2.0 license. It features 280B parameters (A16B architecture), 512K context length, native BF16 and FP8 weights, multimodal understanding of text, image, video, and audio, and built-in MTP speculative decoding. Technical report and model weights are publicly available.
More from Multimodal
- MiniMax Music 3 Goes Open Source, Community Predicts Music Generation Revolution — TheChuckTone · 2026-08-14
- MiniMax H3 Text-to-Video Test: Bowling Scene Looks Impressive — howdyquade · 2026-08-14
- Text-to-Music Models Fail at Hardstyle Kick: A New Benchmark — cephaloform · 2026-08-14
- MiniMax H3 Video Generation Test: User Says 'Having Fun' — esudious · 2026-08-14
- ComfyUI Update: MiniMax H3 Now Supports Anchoring Image and Audio Guides at Any Frame — fruesome · 2026-08-14
- ComfyUI Merges PR: MiniMax H3 Now Supports Image and Audio Guides at Any Frame — fruesome · 2026-08-14