Decide whether one LLM fits one accelerator, at every quantization.
llmVramFitDecide whether one LLM fits one accelerator, at every quantization.
The identical function that renders /lab/llm-vram/{model}/{gpu}. Returns one row per quantization (FP16 through Q3_K_M) with weight bytes and their basis, headroom, the largest context that fits, and the bandwidth-limited decode ceiling; plus the chosen best-fitting quant, the full-precision row, and a five-state verdict. Model geometry comes from each repo’s own config.json and tensor-shape index; accelerator capacity and bandwidth come from the site’s device table.
Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| gpu | Yes | Accelerator slug. | |
| batch | No | Concurrent sequences sharing the cache. Omit it for the published page's 1. | |
| model | Yes | Model slug. | |
| context | No | Context length in tokens used for the headline verdict. Omit it and the solver takes its own default of 8192, which is what the published page states. | |
| kvBytes | No | Bytes per KV cache element: 2 for FP16/BF16 cache, 1 for an 8-bit cache. Omit it for the published page's 2. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| inputs | Yes | The parsed inputs, echoed back with defaults filled in. | |
| result | Yes | The solved analysis. Shape is per-tool. | |
| license | Yes | ||
| provenance | Yes |