← Back to community benchmarks

Qwen35-122B-A10BBF16-GPTQ

M2 Max (38c) · 96 GB · 4bit · 2026-03-20

Performance

8k

tokens

299.1

PP tok/s

18.4

TG tok/s

27388

TTFT (ms)

74.8

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.2.19

macOS macOS 26.3

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	261.6	21.7	72.8 GB	view
4k	300.7	20.7	74.2 GB	view
8k	299.1	18.4	74.8 GB	current
16k	285.9	17.7	76.0 GB	view
32k	259.7	13.4	78.4 GB	view