← Back to community benchmarks

Qwen3.6-35B-A3B-oQ8

M3 Ultra (60c) · 256 GB · 8bit · 2026-04-19
Performance
32k
tokens
1,734
PP tok/s
61.3
TG tok/s
18895
TTFT (ms)
38.5
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,488 85.1 35.4 GB view
8k 2,114 75.0 36.5 GB view
32k 1,734 61.3 38.5 GB current