Open-weight & owned stack · Slms ondevice

Lawyer Runs DeepSeek Locally On Used V100s

Nov 9, 2026, first seen via Tom's Hardware AI

A lawyer reportedly ran DeepSeek V4.1 Flash on eight used Nvidia V100 GPUs at up to 215 tokens per second.

Read the original at tomshardware.comOpens the publisher's site in a new tab

More in Open-weight & owned stack

Google releases open-source TPU Sync inference systemNov 9 AI-Built Adobe Clones Gain Rapid Open-Source AdoptionNov 9 Asahi Linux Switches Code License From MITNov 9 Nous Research Publishes Fine-Tuned Inkling ArtifactsNov 9 Pinterest Deploys Fine-Tuned Qwen3 ModelNov 9