← Back to community benchmarks

DeepSeek-V3.25bit

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

Performance

1k

tokens

192.6

PP tok/s

16.3

TG tok/s

5316

TTFT (ms)

432.4

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.2.12b2

macOS macOS 15.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	192.6	16.3	432.4 GB	current
4k	197.2	15.1	435.8 GB	view
8k	173.1	14.6	440.1 GB	view