Agent skill · software engineering · sickn33
hf-mem
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
Why this skill is useful
Adds specific commands for estimating memory requirements for Hugging Face models that the AI wouldn't reliably generate on its own.
What it needs
Requires uv installed locally. Requires huggingface account access. About 3k tokens when loaded. Last updated 2026-08-07. 44,571 stars on the source repository.
What this skill does
hfmem estimates the required memory for inference, including model weights and an optional KV cache, for Safetensors and GGUF for models on the Hugging Face Hub using HTTP Range requests i.e., without downloading or loading any weights locally. When to use? User asks how much VRAM or memory a model needs to run User wants to know if a model fits on their GPU or a given instance User references a Hugging Face model ID or URL and asks about inference requirements What are the requirements? uv installed (for uvx) HFTOKEN from the host's private credential handling for gated/private repositories; avoid putting tokens in command arguments, logs or reports. A reviewed pinned hf-mem package version and permission to access the requested model metadata. This skill does not bundle the executable. How to run? The angle-bracket and square-bracket forms below are usage notation, not shell commands to paste literally. Quote actual model IDs and file paths. Inspect the selected package's --help, choose a reviewed version (for example with uvx --from "hf-mem==REVIEWEDVERSION" hf-mem ...) and use a private cache where metadata is sensitive. Do not print credentials. Run with --model-id pointing to the Hugging Face Hub repository which will check that it either contains Safetensors (via model.safetensors, model.safetensors.index.json if sharded, or modelindex.json for Diffusers) or GGUF model weights within. If the repository contains GGUF model weights in multiple precisions / quantizations, the estimations will be on a per-file basis, whereas for inference you won't load all of those but rather only a single precision. This being said, for GGUF you might as well need to provide --gguf-file to target the specific file (or path if sharded) you want to run. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sickn33/hf-mem--775b95