← Back to community benchmarks
gemma-4-e4b-it
Performance
32k
tokens
885.3
PP tok/s
46.8
TG tok/s
37013
TTFT (ms)
6.4
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.12
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,020 | 66.8 | 5.6 GB | view |
| 4k | 1,020 | 65.2 | 5.7 GB | view |
| 8k | 999.4 | 61.2 | 5.8 GB | view |
| 16k | 962.2 | 54.6 | 5.9 GB | view |
| 32k | 885.3 | 46.8 | 6.4 GB | current |
| 64k | 775.8 | 34.3 | 7.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 66.8 | 1.00× |
| 2× | 95.7 | 1.43× |
| 4× | 238.8 | 3.57× |