# Self-Hosted Distributions
```{toctree}
:maxdepth: 1
:hidden:

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

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

| **Distribution** 	|           **Llama Stack Docker**           	| Start This Distribution 	|
|:----------------:	|:------------------------------------------:	|:-----------------------:	|
|      Ollama      	|       {dockerhub}`distribution-ollama`       	|       [Guide](ollama)       	|
|        TGI       	|         {dockerhub}`distribution-tgi`        	|       [Guide](tgi)       	|
| vLLM            	|         {dockerhub}`distribution-remote-vllm`        	|       [Guide](remote-vllm)       	|
|  Meta Reference  	| {dockerhub}`distribution-meta-reference-gpu` 	|       [Guide](meta-reference-gpu)       	|
|  Meta Reference Quantized  	| {dockerhub}`distribution-meta-reference-quantized-gpu` 	|       [Guide](meta-reference-quantized-gpu)       	|
|        Together       	|         {dockerhub}`distribution-together`        	|       [Guide](together)       	|
|        Fireworks       	|         {dockerhub}`distribution-fireworks`        	|       [Guide](fireworks)       	|
|        Bedrock       	|         {dockerhub}`distribution-bedrock`        	|       [Guide](bedrock)       	|