0xSero / DeepSeek-V4.1-Flash-1017-EXL3-2.7bpw

Text Generation5155Updated Oct 18, 2026

Downloads

515

Likes

5

Last updated

Oct 18, 2026

License

mit

deepseek-ai/DeepSeek-V4.1-Flash-1017 @ 1bae0e10, quantized with EXL3 trellis coding to fit two NVIDIA DGX Sparks (256 GB together). The routed experts average 2.70 bits per weight (2.90 per decoded token), with each expert's bit width chosen from measured sensitivity. The dens…

Tasks & library

  • text generation
  • vllm

Tags

  • vllm
  • deepseek_v41
  • exl3
  • exllamav3
  • deepseek
  • deepseek-v4.1

Technical specifications

ParametersNot available
Libraryvllm
LanguagesNot available
Licensemit