DeepSeek V4.1 Flash 1017 at EXL3 2.95bpw on dual 3090s: 783 t/s prefill

A user runs DeepSeek V4.1 Flash 1017 locally with EXL3 2.95bpw on two 3090s without NVLink, reaching 783 t/s prefill and planning to share the setup.

Cato Nooka

@catonookaArchived 10 days agoOriginally posted 2026.10.21

Cato Nooka @catonookaOriginally posted 2026.10.21

Open original on X

DeepSeek V4.1 flash 1017 EXL3 2.95bpw - duo 3090 no NVLink Update 4: prefill is now at 783 t/s I am pretty happy with current number, should share the work after real coding work, and hopefully a good PR to Maya repo.

This post quotes another post: x.com/catonooka/status/2112828744226296257

x.com/catonooka/status/2112931301095616724Archived 2026.10.22 12:00

Open original on X