← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Ultra (80c) · 256 GB · 4bit · 2026-03-10

Performance

1k

tokens

2,628

PP tok/s

98.2

TG tok/s

390

TTFT (ms)

20.1

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 256 GB

GPU Cores 80

Software

oMLX v0.2.7

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,628	98.2	20.1 GB	current
4k	2,767	94.9	20.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	98.2	1.00×
2×	174.3	1.77×
4×	287.2	2.92×