Model Releases
don't get distracted by all the hedging words in its name ('flash', minor version): seems like DeepSeek V4.1 Flash is a major update weights…
don't get distracted by all the hedging words in its name ('flash', minor version): seems like DeepSeek V4.1 Flash is a major update weights at: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
don't get distracted by all the hedging words in its name ("flash", minor version): seems like DeepSeek V4.1 Flash is a major update weights at: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash paper at: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/main/DeepSeek_V41_Tech_Report.pdf 🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6
Related
- Model is available here @simonw @ivanfioravanti https://huggingface.co/mlx-community/DeepSeek-V4-Flash-2bit-DQ
- Looks like Llama CPP just merged DFLASH support into main! I wonder how this will stack up against MTP 👀 https://github.com/ggml-org/llama.…
- The new DeepSeek V4.1 Flash model is mindblowing - back on top of the open-source model leaderboard and extremely cheap. It has a lot of ver…
Source: Clem Delangue (X) | 2026-09-10