← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
600.3
PP tok/s
19.0
TG tok/s
6823
TTFT (ms)
8.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 15.1.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 510.8 | 19.4 | 7.9 GB | view |
| 4k | 600.3 | 19.0 | 8.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.4 | 1.00× |
| 2× | 37.5 | 1.93× |
| 4× | 61.2 | 3.15× |