← Back to community benchmarks

DeepSeek-V4-Flash

M3 Ultra (80c) · 256 GB · 4bit · 2026-05-18

Performance

4k

tokens

440.2

PP tok/s

32.1

TG tok/s

9305

TTFT (ms)

142.4

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 256 GB

GPU Cores 80

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	381.8	35.0	142.2 GB	view
4k	440.2	32.1	142.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	35.0	1.00×
2×	53.7	1.53×
4×	78.8	2.25×