← Back to community benchmarks
gemma-4-E4B-it-oQ8
Performance
16k
tokens
4,717
PP tok/s
121.9
TG tok/s
3473
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 | 4,084 | 123.4 | 11.2 GB | view |
| 8k | 4,766 | 130.1 | 11.5 GB | view |
| 16k | 4,717 | 121.9 | 11.8 GB | current |
| 32k | 4,302 | 194.3 | 12.5 GB | view |
| 64k | 3,538 | 99.0 | 13.4 GB | view |
| 128k | 2,702 | 61.2 | 15.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 123.4 | 1.00× |
| 2× | 82.4 | 0.67× |
| 4× | 156.1 | 1.26× |