← Back to community benchmarks

DeepSeek-R1-Distill-Qwen-14B

M4 (10c) · 16 GB · 4bit · 2026-03-16

Performance

4k

tokens

117.9

PP tok/s

10.7

TG tok/s

34746

TTFT (ms)

9.0

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.12

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	124.7	12.0	8.4 GB	view
4k	117.9	10.7	9.0 GB	current
8k	103.3	9.2	9.7 GB	view
16k	91.1	7.4	11.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	12.0	1.00×
2×	23.7	1.97×
4×	28.5	2.38×