← Back to community benchmarks

DeepSeek-R1-0528-Qwen3-8B

M1 (8c) · 16 GB · 4bit · 2026-03-12

Performance

1k

tokens

77.8

PP tok/s

13.0

TG tok/s

13160

TTFT (ms)

4.9

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.9

macOS macOS 26.3

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	13.0	1.00×
2×	17.6	1.35×
4×	18.7	1.44×