← Back to community benchmarks

Qwen3.5-122B-A10B-oQ3.5

M3 Ultra (60c) · 96 GB · 3bit · 2026-04-05
Performance
64k
tokens
1,896
PP tok/s
18.9
TG tok/s
34575
TTFT (ms)
65.7
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.2
macOS macOS 26.4
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 734.6 51.4 60.3 GB view
16k 2,260 20.1 62.4 GB view
64k 1,896 18.9 65.7 GB current