← Back to community benchmarks

community--Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 6bit · 2026-03-30

Performance

8k

tokens

918.9

PP tok/s

27.4

TG tok/s

8915

TTFT (ms)

108.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.24

macOS macOS 26.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,100	37.5	106.1 GB	view
4k	970.8	34.6	107.6 GB	view
8k	918.9	27.4	108.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	37.5	1.00×
2×	43.7	1.17×
4×	58.9	1.57×