← Back to community benchmarks
gemma-4-21b-REAP-Tool-Calling
Performance
4k
tokens
727.7
PP tok/s
66.8
TG tok/s
5629
TTFT (ms)
12.1
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
24 GB
GPU Cores
20
Software
oMLX
v0.3.5
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 649.7 | 71.1 | 11.7 GB | view |
| 4k | 727.7 | 66.8 | 12.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 71.1 | 1.00× |
| 2× | 101.7 | 1.43× |
| 4× | 117.2 | 1.65× |