bartowski's DeepSeek-V4-Flash-GGUF is a quantized GGUF distribution of the DeepSeek-V4-Flash model optimized for local use with tools like llama.cpp. It supports advanced reasoning, tool calling, and thinking modes. The model is hosted on Hugging Face for easy download and local deployment.
DeepSeek V4 Flash sits in PulseGate's Quantised & converted weights category. It focuses on running large reasoning and coding models efficiently on consumer hardware using GGUF format. DeepSeek V4 Flash is an open-source project aimed at developers. DeepSeek V4 Flash is open source under the MIT license. DeepSeek V4 Flash is available on the web, the command line, and API.
Behind DeepSeek V4 Flash is bartowski, and it first shipped in 2023. Development happens publicly on GitHub with 121.2k stars and 1.2k commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 14 similar projects. Among its 3 catalogued features are Local Inference, Quantized Model, and Tool Calling.
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