← Back to community benchmarks
gemma-4-E2B-it
Performance
64k
tokens
3,074
PP tok/s
40.5
TG tok/s
21323
TTFT (ms)
10.8
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
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 4,684 | 52.7 | 9.4 GB | view |
| 4k | 4,767 | 51.6 | 9.5 GB | view |
| 8k | 4,772 | 50.1 | 9.5 GB | view |
| 16k | 4,560 | 48.6 | 9.7 GB | view |
| 32k | 3,910 | 46.7 | 10.0 GB | view |
| 64k | 3,074 | 40.5 | 10.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.7 | 1.00× |
| 2× | 48.1 | 0.91× |
| 4× | 94.8 | 1.80× |
| 8× | 186.1 | 3.53× |