← Back to community benchmarks
gemma-4-26B-A4B-it-oQ6
Performance
32k
tokens
3,082
PP tok/s
70.5
TG tok/s
10632
TTFT (ms)
22.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,119 | 92.8 | 20.7 GB | view |
| 4k | 3,290 | 89.2 | 21.3 GB | view |
| 8k | 3,582 | 85.4 | 21.8 GB | view |
| 16k | 3,399 | 79.8 | 22.0 GB | view |
| 32k | 3,082 | 70.5 | 22.9 GB | current |
| 64k | 2,459 | 56.8 | 24.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 92.8 | 1.00× |
| 2× | 136.1 | 1.47× |
| 4× | 190.4 | 2.05× |