llama.cpp

docs · 74d

Runner · checked 2026-07-10

At a glance

What it's for: Runs a model on the selected hardware.
Cost basis: Price not observed; not treated as free, included, or $0
Build fit: Checked against your current build when you add or replace it; no check means fit is unverified
Still unknown: price, exact provider route. Overall suitability is not verified by these facts.

Specifications

Swipe sideways to see every specification, source, and verification date.

Specification	Value	Source	Verified
Language	C++	github.com/ggml-org/llama.cpp	2026-07-10
Memory floor	—	github.com/ggml-org/llama.cpp	2026-07-10
Context floor	—	github.com/ggml-org/llama.cpp	2026-07-10
Runner type	Model runner	github.com/ggml-org/llama.cpp	2026-07-10
OS support	Windows: Native · macOS: Native · Linux: Native	github.com/ggml-org/llama.cpp	2026-07-10
Consumes API formats	OpenAI	github.com/ggml-org/llama.cpp	2026-07-10
Serves API formats	OpenAI	github.com/ggml-org/llama.cpp	2026-07-10
Model format	GGUF	github.com/ggml-org/llama.cpp	2026-07-10
Web UI	Yes	github.com/ggml-org/llama.cpp	2026-07-10
Flags	Default Server Runtime: false · Default Local Runtime For:	github.com/ggml-org/llama.cpp	2026-07-10

Price evidence

Type	USD	Basis	Conditions	Source	Verified	Freshness
Price not observed.

Price coverage

No reviewed comparable monthly price is on file. Cost remains unknown and is not treated as fixed, included, free, or $0.

Loading current prices and evidence…