← Back to community benchmarks
Step-3___5-Flash
Performance
32k
tokens
565.3
PP tok/s
23.0
TG tok/s
57971
TTFT (ms)
197.1
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.12
macOS
macOS 15.3
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 4k | 620.1 | 35.0 | 195.8 GB | view |
| 32k | 565.3 | 23.0 | 197.1 GB | current |