← Back to community benchmarks

DeepSeek-V3.25bit

M3 Ultra (80c) · 512 GB · 5bit · 2026-03-14

Performance

8k

tokens

161.0

PP tok/s

13.1

TG tok/s

50867

TTFT (ms)

438.3

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.2.12

macOS macOS 15.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	190.6	16.2	432.4 GB	view
4k	186.2	13.6	434.8 GB	view
8k	161.0	13.1	438.3 GB	current