← Back to community benchmarks
gemma-4-e2b-it
Performance
8k
tokens
1,149
PP tok/s
46.4
TG tok/s
7132
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
8 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 15.6.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,197 | 51.8 | 3.8 GB | view |
| 4k | 1,182 | 49.2 | 3.9 GB | view |
| 8k | 1,149 | 46.4 | 4.0 GB | current |
| 16k | 1,079 | 41.6 | 4.0 GB | view |
| 32k | 954.9 | 35.0 | 4.4 GB | view |
| 64k | 758.5 | 26.2 | 5.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.8 | 1.00× |
| 2× | 70.4 | 1.36× |
| 4× | 76.9 | 1.48× |