← Back to community benchmarks
gemma-4-e2b-it
Performance
16k
tokens
3,229
PP tok/s
90.0
TG tok/s
5074
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.8rc1
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,786 | 116.9 | 4.0 GB | view |
| 4k | 3,329 | 110.5 | 4.0 GB | view |
| 8k | 3,499 | 102.6 | 4.1 GB | view |
| 16k | 3,229 | 90.0 | 4.2 GB | current |
| 32k | 2,781 | 28.1 | 5.3 GB | view |
| 64k | 2,113 | 40.6 | 5.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 116.9 | 1.00× |
| 2× | 192.9 | 1.65× |
| 4× | 383.4 | 3.28× |
| 8× | 771.5 | 6.60× |