New in llama.cpp: Model Management

router mode, which lets you dynamically load, unload, and switch between multiple models without restarting.

Reminder: llama.cpp server is a lightweight, OpenAI-compatible HTTP server for running LLMs locally.

This feature was a popular request to bring Ollama-style model management to llama.cpp. It uses a multi-process architecture where each model runs in its own process, so if one model crashes, others remain unaffected.

Start the server in router mode by not specifying a model:

llama-server

This auto-discovers models from your llama.cpp cache (LLAMA_CACHE or ~/.cache/llama.cpp). If you've previously downloaded models via llama-server -hf user/model, they'll be available automatically.

You can also point to a local directory of GGUF files:

llama-server --models-dir ./my-models

Auto-discovery: Scans your llama.cpp cache (default) or a custom--models-dir folder for GGUF files On-demand loading: Models load automatically when first requested LRU eviction: When you hit--models-max (default: 4), the least-recently-used model unloads Request routing: Themodel field in your request determines which model handles it

curl http://localhost:8080/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "ggml-org/gemma-3-4b-it-GGUF:Q4_K_M",
"messages": [{"role": "user", "content": "Hello!"}]
}'

On the first request, the server automatically loads the model into memory (loading time depends on model size). Subsequent requests to the same model are instant since it's already loaded.

curl http://localhost:8080/models

Returns all discovered models with their status (loaded, loading, or unloaded).

curl -X POST http://localhost:8080/models/load \
-H "Content-Type: application/json" \
-d '{"model": "my-model.gguf"}'

curl -X POST http://localhost:8080/models/unload \
-H "Content-Type: application/json" \
-d '{"model": "my-model.gguf"}'

| Flag | Description | |---|---| | --models-dir PATH | Directory containing your GGUF files | | --models-max N | Max models loaded simultaneously (default: 4) | | --no-models-autoload | Disable auto-loading; require explicit /models/load calls |

All model instances inherit settings from the router:

llama-server --models-dir ./models -c 8192 -ngl 99

All loaded models will use 8192 context and full GPU offload. You can also define per-model settings using presets:

llama-server --models-preset config.ini

[my-model]
model = /path/to/model.gguf
ctx-size = 65536
temp = 0.7

The built-in web UI also supports model switching. Just select a model from the dropdown and it loads automatically.

We hope this feature makes it easier to A/B test different model versions, run multi-tenant deployments, or simply switch models during development without restarting the server.