Runs locally on a Mac · by ggml-org

llama.cpp

Run any downloaded chatbot on your Mac and clock its speed.

text, image → text, data · data → data
Access
Official APINo sign-up, no key
To start
FreeOpen source (MIT)
Runs
On your Mac
Checked
Nov 3, 2026Prices as of that day

What it can do 2

Connect compatible downloaded chatbots to appsMetal offload of all layers on M4; keep model+KV < ~10 GBtext, image → text, datafree (local)
Measure how fast a chatbot runs on a Macdata → datafree (local)

Does the same job

Prices and limits as of Nov 3, 2026, from ggml-org’s own pages. They change; check before you rely on them.Not affiliated with ggml-org. Not advice.Something wrong?