← Back to community benchmarks

Qwopus3.5-27B-v3.5-qx86-hi

M4 Max (40c) · 128 GB · 8bit · 2026-04-30

Performance

8k

tokens

207.5

PP tok/s

16.7

TG tok/s

39488

TTFT (ms)

54.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.3

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	226.1	17.9	52.0 GB	view
4k	221.8	17.5	53.4 GB	view
8k	207.5	16.7	54.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.9	1.00×
2×	28.8	1.61×
4×	58.4	3.26×