Open App →
Back to News Feed
Tom's Hardware November 19, 2026 By Shane Downing neutral

Three 'e-waste' Nvidia V100s hit 100 tokens per second on Qwen 3.6 35B in a $1,042 homelab rig

NVIDIA / GPU
A homelab builder runs Qwen 3.6 35B on three used Nvidia Tesla V100 GPUs at about 100 tokens per second, in a $1,042 build.
Read original article ↗

Related Articles

The Jensen Huang Blast Radius Has Hit His Favorite Restaurants

In Taiwan, some food vendors are distancing themselves from Nvidia’s former CEO. Others stand by him. “It’s not as if he

Wired · November 19, 2026

Reducing Rollout Bottlenecks in Reinforcement Learning with NVIDIA Dynamo

Reinforcement learning (RL) uses rewards to train models to solve problems and complete tasks more successfully. Inferen

Nvidia Developer Blog · November 19, 2026

The unfolding Jensen Huang scandal: a timeline

Jensen Huang has resigned from Nvidia following an affair, which could have ramifications for national security as the U

TechCrunch AI · November 19, 2026