← Back to community benchmarks

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

M5 Max (40c) · 64 GB · 8bit · 2026-04-12

Performance

1k

tokens

2,170

PP tok/s

99.3

TG tok/s

472

TTFT (ms)

35.4

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.5.dev1

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,170	99.3	35.4 GB	current
32k	3,243	75.1	38.5 GB	view
64k	2,278	54.1	41.2 GB	view