← Back to community benchmarks
Step-3.5-Flash
Performance
16k
tokens
600.2
PP tok/s
31.4
TG tok/s
27300
TTFT (ms)
196.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.12
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 16k | 600.2 | 31.4 | 196.3 GB | current |
| 32k | 557.1 | 26.5 | 197.1 GB | view |