← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
452.6
PP tok/s
49.0
TG tok/s
2262
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.3.5
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 452.6 | 49.0 | 4.6 GB | current |
| 4k | 498.6 | 45.5 | 4.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.0 | 1.00× |
| 2× | 59.0 | 1.20× |
| 4× | 64.5 | 1.32× |
| 8× | 129.2 | 2.64× |