← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
1,031
PP tok/s
66.2
TG tok/s
3971
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.9rc1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,032 | 70.0 | 5.6 GB | view |
| 4k | 1,031 | 66.2 | 5.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.0 | 1.00× |
| 2× | 113.3 | 1.62× |
| 4× | 127.9 | 1.83× |