← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (60c) · 256 GB · 4bit · 2026-03-31

Performance

8k

tokens

749.2

PP tok/s

46.4

TG tok/s

10935

TTFT (ms)

68.5

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.2.19

macOS macOS 26.3.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	717.4	52.3	66.4 GB	view
4k	764.9	49.8	67.9 GB	view
8k	749.2	46.4	68.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	52.3	1.00×
2×	86.0	1.64×
4×	123.6	2.36×