DeepSeek-V4.1-Flash lands on Nebius: 552B MoE activating 8B with 1M context
Arindam_1729 · x · 2026-09-18
- DeepSeek-V4.1-Flash is now live on Nebius Token Factory, with native image understanding and an architecture built for faster inference on long, input-heavy workflows.
- It's a 552B MoE that activates just 8B parameters for input and 16B for output, with a 1M token context window.
- Developer Arindam built a quick real-time webcam app that feeds multiple frames to the model for scene summarization; he reports it ran smoothly with surprisingly strong results for such a small setup.
More from Models
- 'You Can Feel the Gradient Slopes': Dev Contrasts Benchmaxxed RL Models vs General Ones — theteknosaur · 2026-11-02
- LightOnOCR-3 Launches: Tops FRBench, Adds Layout Structure and Chart Extraction — IgorCarron · 2026-11-02
- NVIDIA's Kumo Is a Family of Four Tabular Foundation Models, Not Just One — pandeyparul · 2026-11-02
- SemiAnalysis: safety classifiers are underrated — Meta's Muse tops cyber benchmark at 35.2% — ThomasScialom · 2026-11-02
- DeepSeek V4.1 Flash 1017 wins over a longtime closed-source-only user: fast, cheap, reliable — _bachrc · 2026-11-02
- Local quants vs Claude on 9 real private bugs: 3-bit costs thinking time, not score — FeydRowan · 2026-11-02