Self-Hosted Distribution

:maxdepth: 2
:hidden:

meta-reference-gpu
meta-reference-quantized-gpu
ollama
tgi
dell-tgi
together
fireworks
remote-vllm
bedrock

We offer deployable distributions where you can host your own Llama Stack server using local inference.

Distribution	Llama Stack Docker	Start This Distribution	Inference	Agents	Memory	Safety	Telemetry
Meta Reference	llamastack/distribution-meta-reference-gpu	Guide	meta-reference	meta-reference	meta-reference; remote::pgvector; remote::chromadb	meta-reference	meta-reference
Meta Reference Quantized	llamastack/distribution-meta-reference-quantized-gpu	Guide	meta-reference-quantized	meta-reference	meta-reference; remote::pgvector; remote::chromadb	meta-reference	meta-reference
Ollama	llamastack/distribution-ollama	Guide	remote::ollama	meta-reference	remote::pgvector; remote::chromadb	meta-reference	meta-reference
TGI	llamastack/distribution-tgi	Guide	remote::tgi	meta-reference	meta-reference; remote::pgvector; remote::chromadb	meta-reference	meta-reference
Together	llamastack/distribution-together	Guide	remote::together	meta-reference	remote::weaviate	meta-reference	meta-reference
Fireworks	llamastack/distribution-fireworks	Guide	remote::fireworks	meta-reference	remote::weaviate	meta-reference	meta-reference
Bedrock	llamastack/distribution-bedrock	Guide	remote::bedrock	meta-reference	remote::weaviate	meta-reference	meta-reference