← Back to community benchmarks
gemma-4-e2b-it
Performance
8k
tokens
4,712
PP tok/s
52.3
TG tok/s
1738
TTFT (ms)
10.1
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.4.1
macOS
macOS 15.7.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 4,553 | 52.4 | 10.0 GB | view |
| 4k | 4,636 | 53.1 | 10.1 GB | view |
| 8k | 4,712 | 52.3 | 10.1 GB | current |
| 16k | 4,463 | 49.3 | 10.2 GB | view |
| 32k | 3,950 | 46.9 | 10.6 GB | view |
| 64k | 3,032 | 41.4 | 11.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.4 | 1.00× |
| 2× | 46.8 | 0.89× |
| 4× | 94.5 | 1.80× |
| 8× | 189.4 | 3.61× |