skill collection · Use or study
hf-mem
Estimate the memory needed to load model weights.
huggingface/skillsskills/hf-mem/SKILL.md
Before you use it
- Input
- A model repository or weight format and the intended inference environment.
- Expected output
- A model-weight memory estimate, not a guarantee that the full application fits.
- Prerequisites
- Review the CLI setup and distinguish weight memory from runtime, context and application overhead.
Publisher guidance starts with hf-cli; other workflows are installed separately. The marketplace entry is not a claim that every workflow is bundled. Review the chosen client's instructions, local hardware, authorization and possible cloud charges. Codex is described without a single surface-specific runtime test; no Codex surface is certified here.
Publisher documentation, static file observations and environment tests are different kinds of evidence. Runtime behavior has not been observed.
Study the method
Study how the workflow narrows an infrastructure question to the model weights.
1 files in the observed scope; 0 in scripts/, 0 in references/, 0 in assets/.
Zero files in scripts/ does not mean no execution, network access or file writes. Markdown and other folders may describe or contain executable behavior.
Source version and requirements
- Observed
- 2026-09-08T11:53:42.181Z
- Source commit
- 97862b0fcc89c850fdd00c82ede1e62d3c930a6d
- Content SHA-256
- ee99f9d97e084aa61a80eaec4e6de2265341e71256d918d48fb87a2ac01ce99f
- License
- Apache-2.0
- Author attribution
- Repository owner: huggingface. Individual authorship is not independently established.
This page describes a pinned source snapshot, not the latest repository state. Changes after this commit have not been reconciled here. A repository license does not necessarily cover external models, datasets or services.
Open current repository ↗