← Back to community benchmarks
Qwen3.6-35B-A3B-TurboQuant
Performance
32k
tokens
4,714
PP tok/s
88.0
TG tok/s
6951
TTFT (ms)
21.4
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,446 | 100.0 | 18.5 GB | view |
| 4k | 2,154 | 96.5 | 19.3 GB | view |
| 8k | 2,292 | 94.7 | 19.6 GB | view |
| 32k | 4,714 | 88.0 | 21.4 GB | current |
| 64k | 3,761 | 82.9 | 22.3 GB | view |
| 128k | 2,478 | 69.1 | 24.2 GB | view |
| 195k | 1,847 | 59.5 | 26.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 100.0 | 1.00× |
| 2× | 154.6 | 1.55× |
| 4× | 199.1 | 1.99× |
| 8× | 395.3 | 3.95× |