gemini-2.5-flash
1 workload result across 1 hardware configuration.
Fastest known config
5.5 decode tok/s
on M3 Pro (18-core GPU) + 36GB unified via hosted-api — see full run
M3 Pro (18-core GPU) + 36GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | hosted-api | — | 5.48tok/s | 159.7tok/s | 676ms | r_sdr-4xjqh0l |