hf-mem

hf-mem is a skill for Claude Code, Codex from waybarrios/opencode-power-pack. It costs 33 tokens per session (1,015 once invoked), scanned A, a copy of hf-mem, MIT.

A command-line tool that estimates how much memory a Hugging Face model needs for inference. Inference means running a trained model to produce outputs, and Safetensors and GGUF are file formats for storing model weights.

In plain words
What is it for?
Use it with a model on the Hugging Face Hub when checking VRAM or system-memory requirements. It supports Safetensors and GGUF repositories and can compare multiple GGUF quantizations.
Why use it?
It helps determine whether a model can fit on a particular GPU or machine before downloading or loading its weights. It can also account for optional KV-cache memory used during text generation.

Skill for Claude CodeCodex

Part of the opencode-power-pack plugin — 54 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/waybarrios/opencode-power-pack/hf-mem
Any agent
npx skills add waybarrios/opencode-power-pack --skill hf-mem
Clone the repo
git clone --depth 1 https://github.com/waybarrios/opencode-power-pack

Made for: Claude Code, Codex.

Or install opencode-power-pack, the plugin that ships this one along with the rest of its 54 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for hf-mem

README.md
[![agentmods](https://agentmods.dev/badge/skills/waybarrios/opencode-power-pack/hf-mem.svg)](https://agentmods.dev/skills/waybarrios/opencode-power-pack/hf-mem)
Your own site
<a href="https://agentmods.dev/skills/waybarrios/opencode-power-pack/hf-mem"><img src="https://agentmods.dev/badge/skills/waybarrios/opencode-power-pack/hf-mem.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,015 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01015
Opus 5 $0.00016 $0.00508
Sonnet 5 $0.00007 $0.00203
Haiku 4.5 $0.00003 $0.00102

Measured 5d ago against content hash 331358ee0263, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hf-mem scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

98% identical to hf-mem — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/hf-mem/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Read the full file on GitHub · 81 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 81 lines · 33 tokens per session scan A 331358ee0263

Subscribe to this mod's changes

hf-mem is a skill published in the GitHub repository waybarrios/opencode-power-pack (490 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 1,015 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to hf-mem, differing in 3 lines, and is treated as a copy.

Related

Other skills, from other repositories

llm-wiki

The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources…

Ar9av/obsidian-wiki · 113 tokens

wiki-export

Export the Obsidian wiki's knowledge graph to structured formats for use in external tools. Use this skill when the user says "export wiki", "export graph", "export to JSON", "export to Gephi", "export to Neo4j", "export to Postgres", "export to SQL", "graphml", "visualize wiki", "knowledge graph export", "export to…

Ar9av/obsidian-wiki · 172 tokens

agent-v3-memory-specialist

Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.

ruvnet/ruflo · 25 tokens

long-context

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases…

davila7/claude-code-templates · 74 tokens

bulk-ingestion

End-to-end discipline for turning any large data source (audio libraries, email takeouts, document corpora, chat exports, API dumps) into brain pages at scale. The lifecycle spine: SCHEMA → ACCESS → TRIAL → EVALUATE → IMPROVE → CODIFY → TEST → SKILLIFY → BULK → MONITOR. State is tracked in a durable JSON manifest (see…

garrytan/gbrain · 114 tokens

cognee-cli

Use when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database migrations.

topoteretes/cognee · 42 tokens