← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-15
Performance
16k
tokens
851.5
PP tok/s
43.7
TG tok/s
19242
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.12
macOS macOS 15.6
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 908.7 47.5 67.0 GB view
16k 851.5 43.7 67.7 GB current