AI Radar
Support
LiveUpdated 2026-11-06 15:10 UTC

mlx-serve

mlx-serve — Tokens per second by chip, GPU cores and memory, measured by the people running the…

mlx-serve is Tokens per second by chip, GPU cores and memory, measured by the people running the models. Not marketing numbers.. It is ranked #5606 on the AI Radar, in Open & local models, first seen 50 days ago and shared in 4 posts (38.1k views).

Visit mlxserve.com

Local LLM Speed on Apple Silicon — Community Benchmarks · mlx-serve Community Benchmarks Tokens per second measured by the people running the models, not by us. Pick your chip to see what to expect, or compare settings to find out which ones are worth turning on. Every result comes from the same pinned workload: a context ladder (512 / 1k / 2k / 4k / 8k / 16k tokens of synthetic code with a planted constant). Run it yourself from the menu bar in MLX-Serve . Chip Any Memory Any Model Any Quality All settings Lossless only View Decode Prefill Speculation headroom Loading results…

Alternatives to mlx-serve

mlx-serve in numbers

FAQ

What is mlx-serve?

Tokens per second by chip, GPU cores and memory, measured by the people running the models. Not marketing numbers. It was first shared on X 50 days ago and is ranked #5606 on the AI Radar.

Is mlx-serve free?

Yes, it is free to use.

Who shared mlx-serve?

4 accounts on X, including @WescheNex1q, in 4 posts totalling 38.1k views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.