Nebius tops MiniMax M3 serving benchmarks with 197.5 tokens/s and 12.04s latency
Arindam_1729 · x · 2026-07-24
A provider benchmark compares inference performance for MiniMax M3 across several hosts.
- Nebius leads on both metrics shown.
- Output speed: 197.5 tokens/s.
- End-to-end response time: 12.04s.
- Other providers in the chart include SiliconFlow, Novita, Together AI, MiniMax, and Parasail (MXP).
- The takeaway is that real-world serving performance can vary substantially depending on provider choice.
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