GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

sm54/deepseek-v4-flash-0731-gguf overview

Built to run with antirez / ds4 inference engine. Not tested or built for llama cpp. Q4K available with dspark drafter.

ggufbase_model:deepseek-ai/DeepSeek-V4-Flash-0731base_model:quantized:deepseek-ai/DeepSeek-V4-Flash-0731region:us

Runs locally from ~5.58 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
2
Pipeline
Author

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
DeepSeek-V4-Flash-0731-DSpark-support.ggufGGUFGGUF5.58 GBDownload
DeepSeek-V4-Flash-0731-Q4KExperts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-noimatrix.ggufGGUFQ4KEXPERTS153.33 GBDownload

Model Details

Model IDsm54/deepseek-v4-flash-0731-gguf
Authorsm54
Pipeline
License
Base modeldeepseek-ai/DeepSeek-V4-Flash-0731
Last modified2026-07-31T16:27:49.000Z

Model README

---

base_model:

  • deepseek-ai/DeepSeek-V4-Flash-0731

---

Built to run with antirez / ds4 inference engine. Not tested or built for llama cpp. Q4K available with dspark drafter.

Run sm54/deepseek-v4-flash-0731-gguf with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models