Evaluating Speed Requires Considering Tokens Needed to Solve
Sentdex · x · 2026-07-03
Sentdex emphasized a crucial factor: how many tokens a model needs to generate a solution. If a model is 2x faster but requires 3x more tokens to complete the task, it isn't actually faster in practice. Therefore, the true metric for comparison should be the "total time to completion" for a task, rather than just raw tokens per second.
More from Infra
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11
- Your p99 latency benchmark may be lying: a deep dive into coordinated omission — Franc0Fernand0 · 2026-09-11