← Back to community benchmarks
gemma-4-e4b-it
Performance
8k
tokens
618.8
PP tok/s
25.9
TG tok/s
13238
TTFT (ms)
5.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 613.8 | 29.4 | 5.4 GB | view |
| 4k | 622.5 | 28.3 | 5.5 GB | view |
| 8k | 618.8 | 25.9 | 5.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.4 | 1.00× |
| 2× | 44.6 | 1.52× |
| 4× | 69.1 | 2.35× |
| 8× | 71.4 | 2.43× |