← Back to community benchmarks
Gemma-4-E2B
Performance
8k
tokens
2,573
PP tok/s
49.0
TG tok/s
3184
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip
M3 Pro (14c)
Memory
18 GB
GPU Cores
14
Software
oMLX
v0.5.3
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,672 | 52.0 | 4.6 GB | view |
| 4k | 2,679 | 52.8 | 4.7 GB | view |
| 8k | 2,573 | 49.0 | 4.8 GB | current |
| 16k | 2,357 | 47.5 | 4.8 GB | view |
| 32k | 2,018 | 41.5 | 5.2 GB | view |
| 64k | 1,553 | 33.7 | 6.0 GB | view |
| 128k | 1,045 | 24.0 | 7.7 GB | view |
| 195k | 771.5 | 18.6 | 9.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.0 | 1.00× |
| 2× | 109.0 | 2.10× |
| 4× | 190.0 | 3.65× |
| 8× | 242.9 | 4.67× |