Skip to main content

Documentation Index

Fetch the complete documentation index at: https://manifest.build/docs/llms.txt

Use this file to discover all available pages before exploring further.

Local model providers run entirely on your own hardware. Manifest detects the running server, fetches the model list, and routes requests to http://localhost:<port> like any other provider. No API key, no network egress, no per-token cost.

Supported runtimes

All three speak OpenAI-compatible /v1/chat/completions and accept any GGUF model file.

Start the server

ollama pull llama3.1:8b   # then:
ollama serve

Connect to Manifest

1

Open the Routing page

In the dashboard, click the runtime tile (Ollama, LM Studio, or llama.cpp).
2

Confirm the server is reachable

Manifest probes http://localhost:<default-port>/v1/models. If the probe succeeds, every loaded model appears for routing.
3

Pin a model to a tier

Open any complexity tier and pick a local model as the primary. You can mix local and cloud models in the same fallback chain.

Running Manifest in Docker

If you self-host Manifest in Docker, the container can’t reach a local server bound to 127.0.0.1 on the host. Two of the three runtimes default to loopback and need an explicit override:
Either flip the GUI toggle (LM Studio → ⚙ Developer → Serve on Local Network) or rebind from the CLI:
lms server start --bind 0.0.0.0 --port 1234 --cors
LM Studio remembers the last --bind, so this is one-time setup.
Inside the Manifest container, the host is reachable as host.docker.internal. Manifest sets this automatically when probing local providers.

Cost & privacy

AspectLocal
API cost$0. The model runs on your hardware.
Network egressNone. Requests never leave the machine.
Cost in dashboardRecorded as 0. Token counts and latency are still tracked.
Pricing dataNot applicable. Local providers are excluded from pricing sync.
Mix local and cloud in one chain: pin a local model to simple for cheap day-to-day calls, fall back to a cloud model when the local server is offline.