← Back to community benchmarks
gemma-4-21b-REAP-Tool-Calling
Performance
32k
tokens
517.4
PP tok/s
51.4
TG tok/s
63330
TTFT (ms)
13.4
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.9
macOS
macOS 15.7.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 32k | 517.4 | 51.4 | 13.4 GB | current |
| 64k | 418.7 | 36.2 | 15.9 GB | view |