← Back to community benchmarks
Qwen3.6-35B-A3B-OptiQ
Performance
64k
tokens
451.8
PP tok/s
33.8
TG tok/s
145058
TTFT (ms)
28.2
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.4.1
macOS
macOS 26.5
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 637.8 | 61.6 | 21.7 GB | view |
| 4k | 743.3 | 58.4 | 22.5 GB | view |
| 8k | 725.7 | 55.6 | 23.0 GB | view |
| 16k | 674.2 | 50.5 | 23.7 GB | view |
| 32k | 582.4 | 44.6 | 25.2 GB | view |
| 64k | 451.8 | 33.8 | 28.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.6 | 1.00× |
| 2× | 93.1 | 1.51× |
| 4× | 111.1 | 1.80× |
| 8× | 132.7 | 2.15× |