← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
630.3
PP tok/s
28.4
TG tok/s
1625
TTFT (ms)
5.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.7rc2
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 630.3 | 28.4 | 5.4 GB | current |
| 4k | 624.0 | 28.0 | 5.5 GB | view |
| 8k | 620.3 | 25.2 | 5.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.4 | 1.00× |
| 2× | 48.5 | 1.71× |
| 4× | 68.8 | 2.42× |
| 8× | 80.2 | 2.82× |