← Back to community benchmarks
gemma-4-26B-A4B-it-qat-OptiQ
Performance
8k
tokens
3,986
PP tok/s
82.9
TG tok/s
2055
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.3
macOS
macOS 26.5.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 8k | 3,986 | 82.9 | 21.0 GB | current |
| 64k | 2,598 | 55.0 | 33.0 GB | view |