124B model runs at 38.7 tok/s on single DGX Spark

A week-long benchmark of a 124B model on one DGX Spark hit 38.7 tok/s on the official INT4 config, 2.4x DeepSeek V4 Flash on the same box. The tester is unaffiliated with the hardware vendor.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Z.ai CEO Jie Tang: GLM 5.3 gains come from RL, not parameter count
- New tool adds 14 skills to Claude Code and Cursor for Markdown diagrams
- Tool turns Claude into a team of AI employees on your Mac
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills