SDKs › llama.cpp: which chips it runs on

llama.cpp: which chips it runs on

llama.cpp and the chips it runs on, with evidence and the date each fact was last checked.

Snapshot 2026-10-15 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

ggml-org (ggml-org/llama.cpp) · runtime. 64 chip entries: runs 41, partial 23.

More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.