← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6-mtp

M3 Max (40c) · 64 GB · 6bit · 2026-05-18
Performance
1k
tokens
1,155
PP tok/s
16.2
TG tok/s
887
TTFT (ms)
29.0
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,155 16.2 29.0 GB current
4k 417.4 73.6 28.4 GB view