← Back to community benchmarks

Qwen3.5-122B-A10B

M2 Ultra (76c) · 192 GB · 8bit · 2026-03-29

Performance

4k

tokens

465.0

PP tok/s

37.7

TG tok/s

8809

TTFT (ms)

123.9

Peak mem (GB)

Hardware

Chip M2 Ultra (76c)

Memory 192 GB

GPU Cores 76

Software

oMLX v0.3.0rc1

macOS macOS 15.7.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	360.2	40.3	122.5 GB	view
4k	465.0	37.7	123.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	40.3	1.00×
2×	65.1	1.62×
4×	87.2	2.16×