← Back to community benchmarks

Qwen3.5-27b-Opus-4.6-Distill-qx64-hi

M4 Max (40c) · 48 GB · 6bit · 2026-03-12

Performance

4k

tokens

265.9

PP tok/s

23.9

TG tok/s

15403

TTFT (ms)

20.2

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.2.8

macOS macOS 15.7

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	262.2	24.6	19.9 GB	view
4k	265.9	23.9	20.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	24.6	1.00×
2×	43.9	1.78×
4×	49.0	1.99×