← Back to community benchmarks

DeepSeek-Coder-V2-Lite-Instruct

M2 (8c) · 16 GB · 4bit · 2026-04-06

Performance

4k

tokens

157.9

PP tok/s

13.3

TG tok/s

25966

TTFT (ms)

10.2

Peak mem (GB)

Hardware

Chip M2 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.3.4

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	202.9	22.3	9.0 GB	view
4k	157.9	13.3	10.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	22.3	1.00×
2×	24.0	1.08×
4×	18.1	0.81×