← Back to community benchmarks

community--Qwen3.6-35B-A3B

M3 Ultra (80c) · 256 GB · 8bit · 2026-04-23

Performance

4k

tokens

2,327

PP tok/s

73.9

TG tok/s

1760

TTFT (ms)

36.2

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 256 GB

GPU Cores 80

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,162	77.4	35.4 GB	view
4k	2,327	73.9	36.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	77.4	1.00×
2×	134.0	1.73×