← Back to community benchmarks

Qwen3.6-35B-A3B

M2 (10c) · 24 GB · 3bit · 2026-05-15

Performance

4k

tokens

206.2

PP tok/s

35.3

TG tok/s

19866

TTFT (ms)

16.0

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.9.dev2

macOS macOS 15.7.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	186.7	37.4	15.2 GB	view
4k	206.2	35.3	16.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	37.4	1.00×
2×	74.7	2.00×
4×	149.5	4.00×