← Back to community benchmarks
gemma-4-e4b-it
Performance
128k
tokens
605.0
PP tok/s
21.3
TG tok/s
216655
TTFT (ms)
12.3
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 846.1 | 42.1 | 9.0 GB | view |
| 4k | 1,018 | 40.6 | 9.1 GB | view |
| 8k | 1,015 | 39.7 | 9.2 GB | view |
| 16k | 975.6 | 37.8 | 9.5 GB | view |
| 32k | 856.8 | 33.6 | 10.2 GB | view |
| 64k | 741.2 | 27.9 | 10.5 GB | view |
| 128k | 605.0 | 21.3 | 12.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.1 | 1.00× |
| 2× | 78.6 | 1.87× |
| 4× | 95.7 | 2.27× |
| 8× | 102.1 | 2.43× |