← Back to community benchmarks

Huihui-Qwen3.5-4B-abliterated

M1 Max (24c) · 32 GB · unknown · 2026-03-11

Performance

4k

tokens

651.0

PP tok/s

29.2

TG tok/s

6292

TTFT (ms)

9.6

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	641.3	29.6	9.4 GB	view
4k	651.0	29.2	9.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	29.6	1.00×
2×	19.1	0.65×
4×	35.3	1.19×