← Back to community benchmarks

Qwen3.5-122B-A10B-Text-mxfp4

M3 Max (30c) · 96 GB · 4bit · 2026-04-03

Performance

1k

tokens

341.6

PP tok/s

38.8

TG tok/s

2998

TTFT (ms)

62.0

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 96 GB

GPU Cores 30

Software

oMLX v0.3.2

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	341.6	38.8	62.0 GB	current
4k	367.5	35.3	63.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	38.8	1.00×
2×	56.3	1.45×
4×	68.8	1.77×