← Back to community benchmarks

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

M4 Pro (16c) · 48 GB · 6bit · 2026-03-11

Performance

4k

tokens

86.6

PP tok/s

9.9

TG tok/s

47311

TTFT (ms)

22.4

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.2.7

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	91.5	9.0	22.0 GB	view
4k	86.6	9.9	22.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	9.0	1.00×
2×	14.8	1.64×
4×	13.2	1.47×