← Back to community benchmarks

Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled

M1 (8c) · 16 GB · 4bit · 2026-04-20

Performance

16k

tokens

311.9

PP tok/s

9.1

TG tok/s

52529

TTFT (ms)

8.2

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	64.6	27.7	6.7 GB	view
4k	71.2	12.2	7.1 GB	view
8k	78.3	12.1	7.4 GB	view
16k	311.9	9.1	8.2 GB	current