← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (60c) · 96 GB · 4bit · 2026-04-16

Performance

8k

tokens

741.8

PP tok/s

50.3

TG tok/s

11043

TTFT (ms)

67.5

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.4

macOS macOS 26.2

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	627.3	56.5	65.6 GB	view
4k	747.2	52.8	66.9 GB	view
8k	741.8	50.3	67.5 GB	current
16k	700.8	41.4	68.7 GB	view
32k	614.2	32.0	71.1 GB	view
64k	428.8	21.7	76.0 GB	view