← Back to community benchmarks
gemma-4-E4B-it-oQ8
Performance
32k
tokens
4,278
PP tok/s
112.5
TG tok/s
7660
TTFT (ms)
12.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.2.dev3
macOS
macOS 26.6
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 4,073 | 127.9 | 11.2 GB | view |
| 8k | 4,782 | 111.4 | 11.5 GB | view |
| 16k | 4,737 | 122.5 | 11.8 GB | view |
| 32k | 4,278 | 112.5 | 12.5 GB | current |
| 64k | 3,645 | 91.0 | 13.4 GB | view |
| 128k | 2,690 | 65.5 | 15.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 127.9 | 1.00× |
| 2× | 79.8 | 0.62× |
| 4× | 136.7 | 1.07× |