← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled

M1 Max (24c) · 32 GB · 4bit · 2026-04-29

User commentMemory Max 21G

Performance

4k

tokens

455.6

PP tok/s

58.2

TG tok/s

8991

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.8rc1

macOS macOS 15.7.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	455.6	58.2	20.0 GB	current
8k	453.4	54.0	20.4 GB	view