← Back to community benchmarks

DeepSeek-R1-Distill-Qwen-7B

M4 (10c) · 16 GB · 4bit · 2026-03-14

Performance

1k

tokens

253.4

PP tok/s

24.1

TG tok/s

4045

TTFT (ms)

4.5

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.8

macOS macOS 15.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	253.4	24.1	4.5 GB	current
4k	245.9	22.7	4.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	24.1	1.00×
2×	47.6	1.98×
4×	60.4	2.51×