← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
389.7
PP tok/s
43.5
TG tok/s
2628
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.3.5.dev1
macOS
macOS 15.6.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 389.7 | 43.5 | 4.6 GB | current |
| 4k | 432.0 | 36.3 | 4.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 43.5 | 1.00× |
| 2× | 46.4 | 1.07× |
| 4× | 54.1 | 1.24× |