ISTA-DASLab Squeezes DeepSeek's 763B Model onto a 12 GB GPU

ISTA-DASLab shrinks DeepSeek-V4.1-Flash-1017 to under 2 bits per weight, letting a 763B MoE run locally on a single 12GB consumer GPU.

Source

AlphaSignal

Published

Oct 24, 2026, 12:34 PM

Author

AlphaSignal Newsroom

Read

1 min read

ISTA-DASLab shrinks DeepSeek-V4.1-Flash-1017 to under 2 bits per weight, letting a 763B MoE run locally on a single 12GB consumer GPU.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Next reads