← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4-mtp

M5 Max (40c) · 48 GB · 4bit · 2026-06-11
Performance
64k
tokens
2,389
PP tok/s
94.1
TG tok/s
27428
TTFT (ms)
25.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.4.3
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 3,391 116.5 23.0 GB view
64k 2,389 94.1 25.7 GB current