An FP8 quantized variant of the DeepSeek-V4 model published by the SGL project. It is optimized for high-throughput inference while maintaining strong performance. Intended for developers building applications that require fast generation from a very large language model.
DeepSeek V4 Flash is a Foundation models & chat product. It focuses on enabling high-speed inference of a large DeepSeek model using reduced precision formats. DeepSeek V4 Flash is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web and API.
Behind DeepSeek V4 Flash is SGL Project, and the product first shipped in 2026. PulseGate's similarity index places it among 11 comparable tools.
Latest indexed changes and source events
sgl-project/DeepSeek-V4-Flash-FP8 verified by the PulseGate indexer
Other apps tracked under the same category.
