← Back to community benchmarks
gemma-4-e4b-it
Performance
4k
tokens
608.1
PP tok/s
18.7
TG tok/s
6735
TTFT (ms)
8.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8.dev1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 614.3 | 19.1 | 8.8 GB | view |
| 4k | 608.1 | 18.7 | 8.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.1 | 1.00× |
| 2× | 37.5 | 1.96× |
| 4× | 60.5 | 3.17× |