← Back to community benchmarks
gemma-4-e4b-it
Performance
1k
tokens
1,072
PP tok/s
41.4
TG tok/s
956
TTFT (ms)
4.3
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,072 | 41.4 | 4.3 GB | current |
| 4k | 1,725 | 40.7 | 4.4 GB | view |
| 8k | 2,044 | 38.8 | 4.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.4 | 1.00× |
| 2× | 85.0 | 2.05× |
| 4× | 115.3 | 2.79× |