← Back to community benchmarks
gemma-4-e4b-it
Performance
64k
tokens
778.9
PP tok/s
36.0
TG tok/s
84139
TTFT (ms)
15.6
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,004 | 66.9 | 13.6 GB | view |
| 4k | 1,020 | 64.1 | 13.7 GB | view |
| 8k | 1,006 | 61.0 | 13.8 GB | view |
| 16k | 971.3 | 55.7 | 14.0 GB | view |
| 32k | 899.7 | 47.0 | 14.7 GB | view |
| 64k | 778.9 | 36.0 | 15.6 GB | current |
| 128k | 616.1 | 24.5 | 16.9 GB | view |
| 195k | 501.5 | 18.5 | 18.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 66.9 | 1.00× |
| 2× | 110.2 | 1.65× |
| 4× | 126.2 | 1.89× |
| 8× | 137.6 | 2.06× |