← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
1,816
PP tok/s
39.8
TG tok/s
2255
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,374 | 41.7 | 4.5 GB | view |
| 4k | 1,816 | 39.8 | 4.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.7 | 1.00× |
| 2× | 82.9 | 1.99× |
| 4× | 105.8 | 2.54× |