← Back to community benchmarks
gemma-4-26B-A4B-it-oQ6
Performance
8k
tokens
3,409
PP tok/s
85.1
TG tok/s
2403
TTFT (ms)
21.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,148 | 93.7 | 20.7 GB | view |
| 4k | 3,136 | 89.3 | 21.4 GB | view |
| 8k | 3,409 | 85.1 | 21.5 GB | current |
| 16k | 3,350 | 79.0 | 22.0 GB | view |
| 32k | 3,079 | 68.6 | 22.9 GB | view |
| 64k | 2,469 | 54.2 | 24.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 93.7 | 1.00× |
| 2× | 136.7 | 1.46× |
| 4× | 190.5 | 2.03× |