← Back to community benchmarks

Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressivemxfp8

M5 Pro (20c) · 64 GB · 8bit · 2026-03-28

Performance

4k

tokens

2,039

PP tok/s

63.5

TG tok/s

2008

TTFT (ms)

35.3

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.23

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,364	66.6	34.4 GB	view
4k	2,039	63.5	35.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	66.6	1.00×
2×	102.1	1.53×
4×	128.4	1.93×