← Back to community benchmarks
gemma-4-e2b-it
Performance
16k
tokens
3,162
PP tok/s
93.3
TG tok/s
5182
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,590 | 117.2 | 3.9 GB | view |
| 4k | 3,558 | 111.3 | 4.0 GB | view |
| 8k | 3,441 | 105.0 | 4.1 GB | view |
| 16k | 3,162 | 93.3 | 4.2 GB | current |
| 32k | 2,761 | 78.4 | 4.5 GB | view |
| 64k | 2,068 | 48.3 | 5.3 GB | view |
| 128k | 728.7 | 26.6 | 7.0 GB | view |
| 195k | 631.6 | 30.0 | 8.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 117.2 | 1.00× |
| 2× | 193.9 | 1.65× |
| 4× | 232.6 | 1.98× |
| 8× | 258.7 | 2.21× |