← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
2,134
PP tok/s
69.9
TG tok/s
7676
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
16,384