← Back to community benchmarks
gemma-4-E4B-it-oQ8
Performance
32k
tokens
1,551
PP tok/s
37.7
TG tok/s
21134
TTFT (ms)
9.9
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
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,730 | 47.5 | 8.9 GB | view |
| 4k | 1,738 | 49.2 | 9.1 GB | view |
| 8k | 1,759 | 45.2 | 9.1 GB | view |
| 16k | 1,687 | 44.3 | 9.3 GB | view |
| 32k | 1,551 | 37.7 | 9.9 GB | current |
| 64k | 1,339 | 31.8 | 10.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.5 | 1.00× |
| 2× | 85.0 | 1.79× |
| 4× | 131.6 | 2.77× |
| 8× | 261.1 | 5.50× |