← Back to community benchmarks
gemma-4-e4b-it
Performance
32k
tokens
908.9
PP tok/s
30.7
TG tok/s
36054
TTFT (ms)
5.5
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 840.0 | 68.7 | 4.6 GB | view |
| 4k | 981.5 | 65.0 | 4.7 GB | view |
| 8k | 992.9 | 60.2 | 4.8 GB | view |
| 16k | 970.9 | 48.4 | 4.9 GB | view |
| 32k | 908.9 | 30.7 | 5.5 GB | current |
| 64k | 796.8 | 17.4 | 6.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 68.7 | 1.00× |
| 2× | 109.7 | 1.60× |
| 4× | 278.0 | 4.05× |