← Back to community benchmarks

baa-ai:Qwen3.5-122B-A10B-MINT-3bit

M2 Max (38c) · 96 GB · 4bit · 2026-03-27

Performance

1k

tokens

209.6

PP tok/s

37.9

TG tok/s

4885

TTFT (ms)

54.0

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.2.23

macOS macOS 15.7.3

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	37.9	1.00×
8×	54.8	1.45×