← Back to community benchmarks

qw3.5-27b-c4.6dst

M5 Max (40c) · 64 GB · 4bit · 2026-04-25

Performance

8k

tokens

739.3

PP tok/s

31.2

TG tok/s

11080

TTFT (ms)

17.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	806.6	33.5	15.8 GB	view
4k	876.2	32.6	17.3 GB	view
8k	739.3	31.2	17.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	33.5	1.00×
2×	54.1	1.61×
4×	63.9	1.91×