← Back to community benchmarks
gemma-4-e4b-it
Performance
8k
tokens
634.7
PP tok/s
32.1
TG tok/s
12907
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 643.3 | 34.1 | 5.4 GB | view |
| 4k | 645.6 | 32.8 | 5.5 GB | view |
| 8k | 634.7 | 32.1 | 5.7 GB | current |
| 16k | 607.8 | 29.7 | 5.9 GB | view |
| 32k | 532.0 | 25.5 | 6.5 GB | view |
| 64k | 450.0 | 20.7 | 7.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.1 | 1.00× |
| 2× | 62.4 | 1.83× |
| 4× | 77.6 | 2.28× |
| 8× | 82.7 | 2.43× |