← Back to community benchmarks

Huihui-GLM-4.7-Flash-abliterated

M4 Max (40c) · 64 GB · 4bit · 2026-03-10

Performance

4k

tokens

1,103

PP tok/s

74.6

TG tok/s

3715

TTFT (ms)

17.6

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.2.7

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,182	83.5	16.4 GB	view
4k	1,103	74.6	17.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	83.5	1.00×
2×	131.6	1.58×
4×	177.4	2.12×
8×	211.1	2.53×