← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (60c) · 256 GB · 8bit · 2026-03-15

Performance

1k

tokens

667.9

PP tok/s

41.6

TG tok/s

1533

TTFT (ms)

123.2

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.2.12

macOS macOS 15.6

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	667.9	41.6	123.2 GB	current
4k	702.7	39.8	123.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	41.6	1.00×
2×	67.3	1.62×
4×	92.2	2.22×