ISTA-DASLab posts 1-bit quantized DeepSeek-V4.1-Flash coder GGUF

A Hugging Face GGUF of DeepSeek-V4.1-Flash-1017 compressed to about 1 bit per parameter, with half its 384 experts per layer removed, yielding 72.1 GB of weights for code and agent workflows.

Name

DeepSeek-V4.1-Flash-1017 GSQ-RCO Coder

Params

763B MoE, 1.05 bits/param

License

MIT

Domain

software

Read it at Hugging Face →

Coverage: 1 sources, in order

1. 03 Nov 11:30 Hugging Face Read the article →

← Front page