← Back to community benchmarks
Qwen3.6-35B-A3B-oQ8-fp16-mtp
Performance
8k
tokens
2,068
PP tok/s
64.0
TG tok/s
3961
TTFT (ms)
37.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.1
macOS
macOS 26.5
Context
8,192