← Back to community benchmarks
gemma-4-e2b-it
Performance
16k
tokens
3,188
PP tok/s
114.3
TG tok/s
5139
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,550 | 120.4 | 6.3 GB | view |
| 4k | 3,446 | 124.4 | 6.3 GB | view |
| 8k | 3,473 | 120.5 | 6.4 GB | view |
| 16k | 3,188 | 114.3 | 6.5 GB | current |
| 32k | 2,736 | 103.3 | 6.9 GB | view |
| 64k | 2,100 | 86.6 | 7.7 GB | view |
| 128k | 1,412 | 56.0 | 9.1 GB | view |
| 195k | 1,050 | 50.2 | 11.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 120.4 | 1.00× |
| 2× | 82.5 | 0.69× |
| 4× | 138.7 | 1.15× |
| 8× | 165.5 | 1.37× |