← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
64k
tokens
2,281
PP tok/s
53.4
TG tok/s
28738
TTFT (ms)
41.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,702 | 95.6 | 35.4 GB | view |
| 4k | 3,480 | 91.6 | 36.2 GB | view |
| 8k | 3,909 | 92.0 | 36.5 GB | view |
| 16k | 3,634 | 83.2 | 37.1 GB | view |
| 32k | 3,230 | 72.2 | 38.5 GB | view |
| 64k | 2,281 | 53.4 | 41.2 GB | current |
| 128k | 1,424 | 26.4 | 46.5 GB | view |
| 195k | 974.2 | 18.2 | 52.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 95.6 | 1.00× |
| 2× | 158.5 | 1.66× |
| 4× | 235.3 | 2.46× |
| 8× | 320.5 | 3.35× |