← Back to community benchmarks

GLM-5-4bit_副本

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-15

Performance

4k

tokens

181.1

PP tok/s

14.2

TG tok/s

22622

TTFT (ms)

394.1

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.2.12

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	182.0	17.3	391.8 GB	view
4k	181.1	14.2	394.1 GB	current