recommend_model
Analyze installed models against detected GPU or CPU memory to pick a provider default, preferring tool-calling models that fit. Set apply=true to write and apply the choice live.
Instructions
Analyze installed models against detected hardware and recommend a default_model for a provider. Prefers tool-calling models that fit the target GPU's free VRAM (or free RAM for CPU-only). With apply=true, writes the pick to the provider's default_model in the config file AND applies it live to this server.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "recommend_model"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| apply | No | Persist the pick to config + apply it live | |
| model | No | Explicit model to set as default with apply:true (must be installed; skips auto-pick) | |
| provider | No | Provider name (default: default_provider) | |
| budget_mb | No | Override the detected memory budget in MB (e.g. when sizing against a remote ollama host manually) |