← Back to community benchmarks
gemma-4-e2b-it
Performance
4k
tokens
1,619
PP tok/s
53.6
TG tok/s
2529
TTFT (ms)
3.0
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,109 | 56.7 | 2.9 GB | view |
| 4k | 1,619 | 53.6 | 3.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.7 | 1.00× |
| 2× | 105.1 | 1.85× |
| 4× | 129.3 | 2.28× |