← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Pro (20c) · 48 GB · 8bit · 2026-05-14
Performance
8k
tokens
2,020
PP tok/s
63.2
TG tok/s
4055
TTFT (ms)
36.5
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 2,020 63.2 36.5 GB current
16k 1,963 58.9 37.4 GB view