← Back to community benchmarks
gemma-4-E2B-it
Performance
4k
tokens
3,852
PP tok/s
26.4
TG tok/s
1064
TTFT (ms)
9.1
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 936.9 | 27.1 | 9.0 GB | view |
| 4k | 3,852 | 26.4 | 9.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.1 | 1.00× |
| 2× | 35.1 | 1.30× |
| 4× | 68.1 | 2.51× |