DeepSeek V4.1 Flash FP8 on 4x RTX PRO 6000: ~200 tok/s

A GCP deployment script runs the abliterated DeepSeek V4.1 Flash in FP8 on four RTX PRO 6000 GPUs at roughly 200 tok/s.

Han Xiao

@hxiaoArchived 9 days agoOriginally posted 2026.10.23

DeepSeek V4.1 Flash FP8 on 4x RTX PRO 6000: ~200 tok/s

Han Xiao @hxiaoOriginally posted 2026.10.23

Joining the DeepSeek-v4.1-Flash-1017-abliterated party. Here’s the deploy script on GCP, 4 rtx6k, fp8, ~200tps. Nothing hillclimbed yet. https://github.com/hanxiao/DeepSeek-V4.1-Flash-1017-FP8-abliterated-4x-RTX-PRO-6000

x.com/hxiao/status/2113479981934518660Archived 2026.10.23 12:06

Open original on X