← Back to community benchmarks
gemma-4-e2b-it
Performance
64k
tokens
1,145
PP tok/s
37.5
TG tok/s
57222
TTFT (ms)
5.2
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.3.8
macOS
macOS 15.6
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,619 | 70.6 | 4.0 GB | view |
| 4k | 1,633 | 67.8 | 4.0 GB | view |
| 8k | 1,630 | 63.7 | 4.1 GB | view |
| 16k | 1,553 | 57.7 | 4.2 GB | view |
| 32k | 1,371 | 49.3 | 4.5 GB | view |
| 64k | 1,145 | 37.5 | 5.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.6 | 1.00× |
| 2× | 91.5 | 1.30× |
| 4× | 103.5 | 1.47× |