← Back to community benchmarks
gemma-4-e4b-it
Performance
128k
tokens
2,140
PP tok/s
28.4
TG tok/s
61253
TTFT (ms)
8.8
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,903 | 80.8 | 5.6 GB | view |
| 4k | 3,761 | 77.0 | 5.7 GB | view |
| 8k | 3,971 | 73.7 | 5.8 GB | view |
| 16k | 3,928 | 67.2 | 6.0 GB | view |
| 32k | 3,568 | 56.0 | 6.4 GB | view |
| 64k | 2,966 | 43.5 | 7.1 GB | view |
| 128k | 2,140 | 28.4 | 8.8 GB | current |
| 195k | 1,572 | 20.9 | 10.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 80.8 | 1.00× |
| 2× | 140.0 | 1.73× |
| 4× | 177.6 | 2.20× |
| 8× | 205.2 | 2.54× |