← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-27
Performance
16k
tokens
2,580
PP tok/s
35.1
TG tok/s
6351
TTFT (ms)
125.4
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.22
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 853.8 32.6 124.3 GB view
4k 937.2 31.7 125.8 GB view
16k 2,580 35.1 125.4 GB current