← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4
Performance
128k
tokens
1,308
PP tok/s
27.4
TG tok/s
100180
TTFT (ms)
30.6
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
131,072