← Back to community benchmarks
gemma-4-e2b-it
Performance
32k
tokens
1,375
PP tok/s
40.6
TG tok/s
23838
TTFT (ms)
4.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,966 | 58.9 | 3.8 GB | view |
| 4k | 1,929 | 55.3 | 3.9 GB | view |
| 8k | 1,795 | 54.1 | 4.0 GB | view |
| 16k | 1,659 | 48.5 | 4.0 GB | view |
| 32k | 1,375 | 40.6 | 4.4 GB | current |
| 64k | 825.0 | 21.8 | 5.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 58.9 | 1.00× |
| 2× | 75.9 | 1.29× |
| 4× | 92.0 | 1.56× |
| 8× | 100.6 | 1.71× |