← Back to community benchmarks
gemma-4-E2B-it-oQ8
Performance
16k
tokens
3,499
PP tok/s
74.4
TG tok/s
4683
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.4.1
macOS
macOS 15.7.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,660 | 79.7 | 5.5 GB | view |
| 4k | 3,535 | 78.8 | 5.6 GB | view |
| 8k | 3,600 | 74.4 | 5.6 GB | view |
| 16k | 3,499 | 74.4 | 5.7 GB | current |
| 32k | 3,117 | 66.2 | 6.0 GB | view |
| 64k | 2,550 | 57.4 | 6.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 79.7 | 1.00× |
| 2× | 154.9 | 1.94× |
| 4× | 233.5 | 2.93× |
| 8× | 458.9 | 5.76× |