← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
506.2
PP tok/s
50.1
TG tok/s
2023
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
16 GB
GPU Cores
19
Software
oMLX
v0.3.5
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 506.2 | 50.1 | 4.6 GB | current |
| 4k | 574.2 | 41.0 | 4.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 50.1 | 1.00× |
| 2× | 67.2 | 1.34× |
| 4× | 74.5 | 1.49× |