← Back to community benchmarks
gemma-4-e4b
Performance
1k
tokens
557.6
PP tok/s
19.3
TG tok/s
1837
TTFT (ms)
7.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.5
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 557.6 | 19.3 | 7.9 GB | current |
| 4k | 620.5 | 19.1 | 8.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.3 | 1.00× |
| 2× | 37.9 | 1.96× |
| 4× | 61.2 | 3.17× |