DeepSeek-V4-Flash-NVFP4 is an NVIDIA-published quantized model checkpoint for local or hosted inference. It provides text and code generation capabilities and is distributed through Hugging Face for developers running compatible machine-learning infrastructure.
In the Quantised & converted weights space, DeepSeek V4 Flash takes a focused approach. It focuses on running an open-weight, quantized language model for text and code generation on compatible NVIDIA hardware. DeepSeek V4 Flash is an open-source project aimed at machine-learning developers. DeepSeek V4 Flash is open source under the Apache-2.0 license. DeepSeek V4 Flash is available on the web, and it can be self-hosted.
It is developed by NVIDIA, and it first shipped in 2024. Development happens publicly on GitHub with 3.4k stars and 336 commits in the last 90 days. PulseGate's similarity index places it among 13 comparable projects. Key capabilities include text generation, code generation, and multimodal input.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do