← Back to community benchmarks
gemma-4-E2B-it-oQ4
Performance
16k
tokens
2,703
PP tok/s
78.8
TG tok/s
6061
TTFT (ms)
3.7
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9rc1
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,922 | 90.3 | 3.5 GB | view |
| 4k | 3,088 | 86.4 | 3.6 GB | view |
| 8k | 3,079 | 82.9 | 3.6 GB | view |
| 16k | 2,703 | 78.8 | 3.7 GB | current |
| 32k | 2,487 | 69.1 | 4.1 GB | view |
| 64k | 1,981 | 56.2 | 4.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 90.3 | 1.00× |
| 2× | 132.0 | 1.46× |
| 4× | 169.7 | 1.88× |
| 8× | 176.4 | 1.95× |