← Back to community benchmarks
gemma-4-E4B-it-oQ8
Performance
16k
tokens
4,209
PP tok/s
96.0
TG tok/s
3893
TTFT (ms)
11.8
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
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,968 | 108.3 | 11.2 GB | view |
| 8k | 4,741 | 101.2 | 11.5 GB | view |
| 16k | 4,209 | 96.0 | 11.8 GB | current |
| 32k | 4,275 | 88.4 | 12.5 GB | view |
| 64k | 3,648 | 74.5 | 13.4 GB | view |
| 128k | 2,700 | 47.0 | 15.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 108.3 | 1.00× |
| 2× | 66.6 | 0.61× |
| 4× | 144.7 | 1.34× |