AGENT SKILL

hf-mem

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

License 许可
Apache-2.0
最近更新
2026-11-11
Stars
★ 2
Forks
0

01 前言 Front Matter

name
hf-mem
description
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

02 资源文件 2

03 SKILL.md 正文

hf_mem 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)
  • HF_TOKEN env var or --hf-token flag (for gated or private models only)

How to run?

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 model_index.json for Diffusers) or GGUF model weights within.

uvx hf-mem --model-id <model-id> --json-output

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.

uvx hf-mem --model-id <model-id> --gguf-file <file-or-path> --json-output

Additionally, hf-mem comes with an --experimental flag that will also calculate the KV cache memory requirements too, useful for large-language models, meaning it applies to LLMs (...ForCausalLM), VLMs (...ForConditionalGeneration), and GGUF models.

As per the context window, it will be read from the default or overridden with --max-model-len a la vLLM. And, same goes for the KV cache precision, which will default to the model precision unless manually set via --kv-cache-dtype a la vLLM too.

For Safetensors use as:

uvx hf-mem --model-id <model-id> --experimental [--max-model-len N] [--batch-size N] [--kv-cache-dtype auto|bfloat16|fp8|fp8_ds_mla|fp8_e4m3|fp8_e5m2|fp8_inc] --json-output

And, for GGUF use as:

uvx hf-mem --model-id <model-id> --gguf-file <file-or-path> --experimental [--max-model-len N] [--batch-size N] [--kv-cache-dtype auto|F32|F16|Q4_0|Q4_1|Q5_0|Q5_1|Q8_0|Q8_1|Q2_K|Q3_K|Q4_K|Q5_K|Q6_K|Q8_K|IQ2_XXS|IQ2_XS|IQ3_XXS|IQ1_S|IQ4_NL|IQ3_S|IQ2_S|IQ4_XS|I8|I16|I32|I64|F64|IQ1_M|BF16|TQ1_0|TQ2_0|MXFP4] --json-output

Examples

For Transformers with Safetensors weights:

uvx hf-mem --model-id MiniMaxAI/MiniMax-M2 --json-output

For Diffusers with Safetensors weights:

uvx hf-mem --model-id Qwen/Qwen-Image --json-output

For Sentence Transformers with Safetensors weights:

uvx hf-mem --model-id google/embeddinggemma-300m --json-output

With --experimental to include the KV cache estimation for LLMs and VLMs:

uvx hf-mem --model-id mistralai/Mistral-7B-v0.1 --experimental --json-output

And, for LLMs or VLMs with GGUF weights:

uvx hf-mem --model-id unsloth/Qwen3.5-397B-A17B-GGUF --gguf-file Q4_K_M --experimental --json-output

04 同仓库更多 Skills

tangyixiao
tangyixiao/tangyixiao-skills

xlsx

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

★ 2
tangyixiao
tangyixiao/tangyixiao-skills

writing-shape

Writing, exploit: shape raw material into an article, paragraph by paragraph.

★ 2
tangyixiao
tangyixiao/tangyixiao-skills

writing-fragments

Writing, explore: mine raw fragments, no structure yet.

★ 2
tangyixiao
tangyixiao/tangyixiao-skills

writing-for-agents

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

★ 2
tangyixiao
tangyixiao/tangyixiao-skills

writing-clearly-and-concisely

Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

★ 2
tangyixiao
tangyixiao/tangyixiao-skills

writing-beats

Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.

★ 2