← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
447.5
PP tok/s
30.2
TG tok/s
2288
TTFT (ms)
5.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 447.5 | 30.2 | 5.4 GB | current |
| 4k | 454.5 | 30.0 | 5.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.2 | 1.00× |
| 2× | 44.2 | 1.46× |
| 4× | 55.0 | 1.82× |