← Back to community benchmarks
gemma-4-e2b-it
Performance
4k
tokens
638.2
PP tok/s
29.4
TG tok/s
6418
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M1 (7c)
Memory
8 GB
GPU Cores
7
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 550.8 | 31.3 | 3.8 GB | view |
| 4k | 638.2 | 29.4 | 3.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.3 | 1.00× |
| 2× | 40.9 | 1.31× |
| 4× | 47.1 | 1.50× |