← Back to community benchmarks
Gemma-4-E2B
Performance
4k
tokens
2,079
PP tok/s
63.3
TG tok/s
1971
TTFT (ms)
3.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,552 | 66.6 | 2.9 GB | view |
| 4k | 2,079 | 63.3 | 3.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 66.6 | 1.00× |
| 2× | 125.8 | 1.89× |
| 4× | 251.9 | 3.78× |