Hugging Face hf-mem

VRAM estimate via HTTP Range, no download. Needs uvx. Gated models need HF_TOKEN

Hugging Face · Apache-2.0

When

Estimate VRAM/memory to load Safetensors or GGUF from the Hub via HTTP Range \u2014 no weight download. Needs uvx. Gated/private models need HF_TOKEN. Distinct from huggingface-local-models (actually running GGUF).

The Catch

VRAM estimate via HTTP Range, no download. Needs uvx. Gated models need HF_TOKEN. Distinct from huggingface-local-models. Does not train or host.

Embed

Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.

Markdown

[![Reviewed on Stack Gems](https://stackgems.com/badge/skill/huggingface-hf-mem.svg)](https://stackgems.com/skills/huggingface-hf-mem)