MiniMax-M3.1-Flash launches on SiliconFlow on its first day as an open-weight model
🐰 Space Bunny just went open-weight!
AI BriefingSiliconFlow announced that MiniMax-M3.1-Flash went live on its platform on the first day of its open-weight release. The model scored 73.7% on DeepSWE v1.1 and 61.7 on OSWorld V2, natively supports text, image, and video inputs with a 1M context window, and uses an MSA architecture with full-layer sparse attention. Its inference speed is nearly 3 times faster than M3, while the cost of agent tasks is reduced by 70%.
Source: SiliconFlow · x.com
Event follow-up3
View all event coverage- Unsloth releases quantized MiniMax-M3.1-Flash GGUF; the 2-bit version can run locally with 150GB of memoryUnsloth · 21 days ago
- MiniMax releases M3.1 Flash weights: 428B total parameters, 23B active per tokenMiniMax · 25 days ago
- MiniMax released M3.1 Flash, nearly tripling inference speed and reducing usage costs by 70%MiniMax:Blog · 28 days ago