Hugging Face · #38

deepseek-ai/DeepSeek-V4-Flash-0731

deepseek-ai/DeepSeek-V4-Flash-0731 is a 304B text-generation model on Hugging Face. Run locally: llama-cli -hf deepseek-ai/DeepSeek-V4-Flash-0731 or ollama run hf.co/deepseek-ai/DeepSeek-V4-Flash-0731. 4,083 Hugging Face likes (#38 in this directory).

Model
https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
Author
deepseek-ai (org)
Likes
4,083
Downloads (30 days)
4,241,430
Task
text-generation
Library
transformers
License
mit
Parameters
304B
Gated
No
Created
2026-07-31
Last modified
2026-08-01
Snapshot
2026-10-29

Run it locally.

Shadowfetch Linux is a Debian testing desktop with KDE Plasma, local AI tools, and ShadowCode. ShadowCode's bundled llama.cpp runs GGUF models; you can also use llama.cpp or Ollama from the terminal.

llama.cpp

llama-cli -hf deepseek-ai/DeepSeek-V4-Flash-0731

Ollama

ollama run hf.co/deepseek-ai/DeepSeek-V4-Flash-0731

These commands work when this repo, or a GGUF quant of it, publishes GGUF weights. They do not invent a quant name. For safetensors-only repos, convert with llama.cpp or use a GGUF repo on the Hub.

ShadowCode prompt.

Paste this into ShadowCode after you open Settings › Local models.

In Settings › Local models, run deepseek-ai/DeepSeek-V4-Flash-0731 only if a GGUF file is available. If the Hub repo is safetensors-only, use a GGUF quant instead of guessing a filename. Ask before downloading.

Download Shadowfetch Linux — ISO, checksum and signature.

Back to Hugging Face models · Methodology