← Back to community benchmarks

Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled

M5 Pro (20c) · 64 GB · 4bit · 2026-03-15

Performance

64k

tokens

1,222

PP tok/s

35.5

TG tok/s

53642

TTFT (ms)

22.5

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.13

macOS macOS 26.3.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	1,885	76.6	20.0 GB	view
32k	1,643	65.2	20.8 GB	view
64k	1,222	35.5	22.5 GB	current