← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
32k
tokens
3,380
PP tok/s
81.5
TG tok/s
9695
TTFT (ms)
38.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 26.5.2
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,388 | 91.0 | 35.4 GB | view |
| 4k | 4,118 | 91.0 | 36.2 GB | view |
| 8k | 4,400 | 90.8 | 36.6 GB | view |
| 16k | 4,035 | 86.9 | 37.7 GB | view |
| 32k | 3,380 | 81.5 | 38.9 GB | current |
| 64k | 2,413 | 70.3 | 41.9 GB | view |
| 128k | 1,376 | 54.9 | 48.2 GB | view |
| 195k | 875.2 | 38.4 | 55.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 91.0 | 1.00× |
| 2× | 159.6 | 1.75× |
| 4× | 223.1 | 2.45× |
| 8× | 296.6 | 3.26× |