Fit check
fit_checkCheck whether a model fits on this machine and where it will run by estimating weights and KV cache against free VRAM and RAM, returning GPU, partial GPU+CPU, CPU, or none.
Instructions
Will a model run on this machine, and where? Uses the installed model's size and exact layer architecture when the runtime exposes it (else parameter-count or catalog estimates) to size weights + KV cache for a context length, then compares with free VRAM summed across GPUs and available RAM. Returns target gpu / partial (GPU+CPU split) / cpu / none, with the numbers and how the KV estimate was made. Credits back memory the model already uses if it is loaded.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"model": "<model>"
},
"name": "fit_check"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | Model id/name to check | |
| provider | No | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). | |
| sizeBytes | No | Explicit weight size in bytes (overrides lookup) | |
| kvCacheType | No | KV cache precision: f16 (default), q8_0, q4_0 | |
| contextLength | No | Context length for the KV-cache estimate (default 4096) | |
| parameterSize | No | Parameter size like "7B" (overrides lookup) |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| fits | Yes | ||
| note | Yes | ||
| model | Yes | ||
| loaded | Yes | ||
| target | Yes | ||
| sizeSource | Yes | ||
| requiredBytes | Yes | ||
| availableBytes | Yes |