← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-04-16
Performance
64k
tokens
2,216
PP tok/s
67.3
TG tok/s
29579
TTFT (ms)
25.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 3,302 92.0 23.0 GB view
64k 2,216 67.3 25.7 GB current