← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-DistilledoQ4-MTP

M4 Pro (20c) · 48 GB · 4bit · 2026-05-18

Performance

4k

tokens

905.8

PP tok/s

83.7

TG tok/s

4522

TTFT (ms)

20.5

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	778.5	89.6	19.7 GB	view
4k	905.8	83.7	20.5 GB	current
8k	890.7	78.7	21.0 GB	view