#performance
2 articles
- 2026-10-17
Tokens Per Second Is Two Benchmarks Wearing a Trench Coat
A single tokens-per-second score hides prompt ingestion, decoding, and the workload that actually matters. Benchmark both halves or stop comparing machines.
- 2026-03-05
Which Local LLM Is Fastest on Ryzen AI Max+ 395? I Benchmarked 10 of Them
Real prefill and generation speeds for 10 local LLMs on Strix Halo — and the winner surprised me.