← Back to community benchmarks
gemma-4-e2b-it
Performance
64k
tokens
1,196
PP tok/s
39.7
TG tok/s
54810
TTFT (ms)
5.2
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.3.12
macOS
macOS 26.5
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,834 | 73.8 | 4.0 GB | view |
| 4k | 1,823 | 63.5 | 4.0 GB | view |
| 8k | 1,785 | 67.2 | 4.1 GB | view |
| 16k | 1,669 | 61.8 | 4.2 GB | view |
| 32k | 1,474 | 50.8 | 4.5 GB | view |
| 64k | 1,196 | 39.7 | 5.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.8 | 1.00× |
| 2× | 88.7 | 1.20× |
| 4× | 109.9 | 1.49× |
| 8× | 106.4 | 1.44× |