← Back to community benchmarks
gemma-4-E4B-it
Performance
4k
tokens
638.0
PP tok/s
19.4
TG tok/s
6420
TTFT (ms)
8.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 625.3 | 19.7 | 8.8 GB | view |
| 4k | 638.0 | 19.4 | 8.9 GB | current |
| 64k | 458.9 | 14.4 | 10.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.7 | 1.00× |
| 2× | 38.1 | 1.93× |
| 4× | 58.4 | 2.96× |