Agent Docs

GPU memory check: per-GPU estimate of weights+KV-cache VRAM, max context, and smaller-quant options. An estimate, not a run test.

Alias of /api/v1/artifacts/{id}/fit (recorded; identical handler). Prefer the recorded path: this one already answers with Deprecation and Sunset headers.

Inputs. Path, query and header fields are listed below. No request body is required.

Outputs. See each status below for its media type, schema and headers. A missing record or unavailable capability is not a successful empty result.

Errors. API JSON failures use the documented response schema. Read code, message and next; retry only when the response allows it. Auth, invalid input and missing records need a caller change.

Rate limits. Public read budgets apply by client IP and route group. This operation can have a smaller route-specific budget. Read Retry-After on 429 or retryable 503 responses.

Example setup. Use an identifier returned by the matching list, search or create operation. Sample identifiers are not a promise that a record exists.

get/api/artifacts/{id}/fit

Request

  • Base URL: https://huggingbay.xyz
  • URL: https://huggingbay.xyz/api/artifacts/{id}/fit
  • Auth: none declared

Path parameters

idstring required

Query parameters

gpustring

GPU id (e.g. rtx4090-24, rtx3090-24, a100-80, h100-80, mac-m3-max-64).

ctxinteger
batchinteger

Response

Per-GPU memory estimate report

object required

Per-GPU memory estimate report. Fields can vary; no stronger field guarantee is specified for this operation.

Changes

No recorded changes to this operation across all 1 revision of this API.