← Back to community benchmarks

Qwen3.6-35B-A3B-PARO

M3 Ultra (60c) · 256 GB · 4bit · 2026-06-07
Performance
4k
tokens
2,121
PP tok/s
73.1
TG tok/s
1931
TTFT (ms)
19.3
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.4.2rc1
macOS macOS 26.5.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,558 73.7 18.6 GB view
4k 2,121 73.1 19.3 GB current
8k 2,108 70.6 19.7 GB view
16k 1,966 70.9 20.3 GB view
32k 1,680 65.5 21.6 GB view
64k 1,280 56.1 24.3 GB view