DeepSeek releases DeepSeek-V4-Flash-0731 on Hugging Face

How this story unfolded

4 weeks · 10 reports · 47 community posts · 57 of 62 shown

1. Jul 8
   • unsloth/DeepSeek-V4-Flash-GGUFhuggingface.co
2. Jul 10
   • DeepSeek v4 Flash on 4090 + DDR5, my experience
3. Jul 16
   • 2 community posts
4. Jul 17
   • DeepSeek v4 Flash on 5090 in llama.cpp with 1 Million context
5. Jul 31
   • DeepSeek Unveils Public Beta API for Flagship AI Modelbloomberg.com
   • DeepSeek puts V4-Flash API into public betatechnode.com
   • deepseek-ai/DeepSeek-V4-Flash-0731huggingface.co
   • unsloth/DeepSeek-V4-Flash-0731-GGUFhuggingface.co
   • DeepSeek V4 Flash now runs updated weights on AI Gatewayvercel.com
   • DeepSeek Upgrades DeepSeek-V4-Flash-0731 with Major Agentic and Coding Gainsmarktechpost.com
   • 23 community posts
6. Aug 1
   • 9 community posts
7. Aug 2
   • 2 community posts
8. Aug 3
   • Deepseek v4 flash - 100-150 faster t/s in prefill/pp.
9. Aug 4
   • DeepSeek V4 Flash is 90% off through Novita on AI Gatewayvercel.com
   • 1 line of code in @aisdk saves you 90% or more in DeepSeek v4 Flash AI Gateway tokens
10. Aug 5
    • DeepSeek V4 Flash tops OpenRouter weekly ranking with 7.22 trillion tokenstechnode.com
    • 3 community posts
11. Aug 6
    • I remember a time when 'flash' meant 32B
12. Aug 7
    • DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and Codingtogether.ai
    • 3 community posts