← Back to community benchmarks

Huihui-Qwen3.5-27B-abliterated

M4 Max (32c) · 36 GB · 6bit · 2026-03-12

Performance

4k

tokens

165.0

PP tok/s

13.2

TG tok/s

24817

TTFT (ms)

22.4

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.2.8

macOS macOS 26.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	168.2	14.4	22.1 GB	view
4k	165.0	13.2	22.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	14.4	1.00×
2×	19.3	1.34×
4×	14.6	1.01×