← Back to community benchmarks
Qwen3.6-35B-A3B-oQ3
Performance
64k
tokens
1,369
PP tok/s
27.8
TG tok/s
47861
TTFT (ms)
21.4
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.2
Context
65,536