← Back to community benchmarks
gemma-4-26B-A4B-it-oQ6
Performance
32k
tokens
2,924
PP tok/s
65.8
TG tok/s
11208
TTFT (ms)
24.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.12
macOS
macOS 26.6
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,128 | 89.7 | 22.4 GB | view |
| 4k | 3,071 | 87.7 | 23.0 GB | view |
| 8k | 3,355 | 84.7 | 23.2 GB | view |
| 16k | 3,219 | 76.5 | 23.7 GB | view |
| 32k | 2,924 | 65.8 | 24.6 GB | current |
| 64k | 2,404 | 53.7 | 26.6 GB | view |
| 128k | 1,674 | 37.5 | 30.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 89.7 | 1.00× |
| 2× | 130.4 | 1.45× |
| 4× | 187.5 | 2.09× |