← Back to community benchmarks

DeepSeek-R1-Distill-Qwen-7B

M5 (10c) · 24 GB · 4bit · 2026-05-18

Performance

1k

tokens

274.8

PP tok/s

29.5

TG tok/s

3730

TTFT (ms)

4.5

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	274.8	29.5	4.5 GB	current
4k	267.3	27.8	5.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	29.5	1.00×
2×	59.2	2.01×
4×	71.9	2.44×