← Back to community benchmarks

community--Qwen3.5-122B-A10B

M3 Ultra (60c) · 96 GB · 4bit · 2026-03-30
Performance
4k
tokens
762.9
PP tok/s
45.2
TG tok/s
5369
TTFT (ms)
67.9
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.2.24
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 715.6 47.4 66.4 GB view
4k 762.9 45.2 67.9 GB current
8k 749.1 42.5 68.5 GB view
Batching Results
Batch Size TG tok/s Speedup
47.4 1.00×
76.6 1.62×
109.8 2.32×