← Back to community benchmarks

Qwen3.5-27B-Claude-4.6-Opus-Distilled

M4 Pro (20c) · 64 GB · 4bit · 2026-03-10

Performance

1k

tokens

123.6

PP tok/s

15.5

TG tok/s

8283

TTFT (ms)

15.8

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.6

macOS macOS 26.3

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.5	1.00×
2×	27.7	1.79×
4×	30.5	1.97×