Data & Analysis hugging-face-hubsafetensorsggufvram-estimationkv-cacheuvx

Hugging Face Model Memory Estimator

Estimate inference memory without downloading model weights.

FollowSkills review · FSRS-2.0
Not recommended
44/ 100 5-point scale 2.2 / 5
Trust13 / 25 · 2.6/5

The document discloses that HTTP Range requests are used against the Hugging Face Hub and that HF_TOKEN is needed only for gated or private models, making the main data flow visible. However, it runs an unpinned external CLI through uvx and does not explain token protection, user confirmation, permission isolation, failure recovery, or rollback, so 12 points are deducted. No credential theft, covert exfiltration, or destructive default is evident.

Reliability7 / 20 · 1.8/5

The commands, Safetensors/GGUF branches, and main options are internally consistent, making the happy path plausible. However, there is no version pinning, committed test suite, example failure output, abnormal-input handling, or diagnostic guidance, and execution was not performed here. Static calibration therefore limits this to 7 points.

Adaptability9 / 15 · 3.0/5

The intended scenarios, model ID, GGUF file, experimental mode, and JSON output are clearly described, with examples for Transformers, Diffusers, Sentence Transformers, and LLM/VLM use. Non-fit boundaries, estimation-error limits, trigger exclusions, Chinese-language support, and mainland-China reachability are not documented; the core path depends on the Hugging Face Hub and package retrieval through uv, so points are deducted.

Convention7 / 15 · 2.3/5

The SKILL.md is concise and includes trigger conditions, requirements, commands, parameters, and examples. The repository supplies an Apache-2.0 license and CI validation for generated artifacts. The skill itself lacks versioning, changelog, explicit maintenance ownership or update path, troubleshooting, limitation disclosure, and output-field explanations, warranting a mid-range score.

Effectiveness5 / 15 · 1.7/5

The commands produce JSON memory estimates directly usable for the stated task and cover both weights and optional KV-cache requirements. However, there are no committed real execution results, accuracy validation, or comparative evidence, and the estimation boundaries are incomplete. Static calibration limits the score to 5.

Verifiability3 / 10 · 1.5/5

The source provides auditable commands, parameters, and examples, while repository CI can validate generated-file consistency. There is no evidence of tests covering hf-mem key paths, real outputs, third-party review, or corroboration across independent sources. Evidence is therefore limited to 3 points.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 86cdeee824b7
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • uvx may retrieve and execute an unpinned tool from an external source; verify package provenance, version, and execution isolation.
  • The skill accesses the Hugging Face Hub; HF_TOKEN for private or gated models must not appear in commands, logs, or output.
  • Mainland-China reachability, failure handling, estimation error, and output-field semantics are undocumented; add these limitations and perform real validation before deployment.
Review evidence [1][2][3][4][5]
See the full review method →

What does this skill do, and when should you use it?

hf-mem is a focused skill in the Hugging Face Skills repository for estimating the memory needed to run models hosted on the Hugging Face Hub. It supports Safetensors and GGUF weights and uses HTTP Range requests, so weights do not need to be downloaded or loaded locally. The standard estimate covers model weights, while --experimental can add KV-cache requirements for supported LLMs, VLMs, and GGUF models. It is a good fit for pre-deployment hardware planning when the model repository and target inference settings are known.

Runs the hf-mem CLI against a Hugging Face Hub model repository and returns JSON memory estimates for Safetensors or GGUF weights. For repositories containing multiple GGUF precisions or quantizations, it can estimate each file or target a selected file or sharded path with --gguf-file. With --experimental, it calculates KV-cache memory using the context length, batch size, and KV-cache precision supplied by the user or inferred from defaults.

  1. A developer wants to estimate VRAM before running a Hugging Face model locally.
  2. An ML engineer needs to check whether a model fits a particular GPU or compute instance.
  3. A user provides a Hugging Face model ID or URL and asks about inference requirements.
  4. A practitioner needs per-file memory estimates for different GGUF quantizations in one repository.

What are this skill's strengths and limitations?

Pros
  • Supports both Safetensors and GGUF weights.
  • Uses HTTP Range requests without downloading or locally loading model weights.
  • Provides JSON output for automation.
  • Experimental mode includes KV-cache estimates and exposes context-length, batch-size, and cache-precision controls.
Limitations
  • Requires uv and network access to the Hugging Face Hub.
  • GGUF repositories with multiple quantizations may require manual file selection.
  • KV-cache estimation is explicitly experimental.
  • The supplied material gives no test-suite, performance, or cross-platform validation evidence.

How do you install this skill?

Copy or symlink the skills/hf-mem/ folder into an Agent Skills directory supported by the client, such as Codex's $REPO_ROOT/.agents/skills or $HOME/.agents/skills. The README also documents hf skills add <skill-name> for adding other Hugging Face skills, but it does not provide a separate hf-mem package or versioned installation command.

How do you use this skill?

Install uv, then run:
uvx hf-mem --model-id <model-id> --json-output
For a specific GGUF file, run:
uvx hf-mem --model-id <model-id> --gguf-file <file-or-path> --json-output
Add --experimental to estimate KV-cache memory, optionally setting --max-model-len, --batch-size, and --kv-cache-dtype. For gated or private models, provide HF_TOKEN or pass --hf-token.

FAQ

Does it download model weights?
No. The skill states that it uses HTTP Range requests and does not download or locally load Safetensors or GGUF weights.
What is needed for private or gated models?
Use the HF_TOKEN environment variable or the --hf-token flag. The source does not require a token for public models.
Can it estimate KV-cache memory?
Yes. Use --experimental; it applies to LLMs, VLMs, and GGUF models, with options for maximum model length, batch size, and KV-cache data type.
Does the source state how much it costs to use?
No. The supplied material does not state pricing for hf-mem, Hugging Face Hub access, or the compute instances being evaluated.

More skills from this repository

All from huggingface/skills

Dev & Engineering

Hugging Face Local Model Runner

Choose compatible GGUF quantizations from Hugging Face and run them locally with llama.cpp.

Data & Analysis

Sentence Transformers Training Assistant

Train retrieval, similarity, reranking, and sparse-search models with Sentence Transformers.

Dev & Engineering

Hugging Face MCP Assistant

Connect agents to Hugging Face Hub for searchable models, datasets, documentation, apps, and compute jobs.

Writing & Content

Hugging Face Paper Publisher

Publish, connect, and manage research papers on the Hugging Face Hub.

Data & Analysis

Hugging Face LLM Trainer

Train, fine-tune, and preserve models on Hugging Face cloud GPUs.

Dev & Engineering

Hugging Face Hub CLI Skill

Give agents command-line control over Hugging Face Hub models, datasets, Spaces, jobs, and infrastructure.

Dev & Engineering

Hugging Face ZeroGPU Builder

Build dependable Gradio AI demos and GPU workloads on Hugging Face ZeroGPU.

Dev & Engineering

LoRA Space Demo Builder

Build and publish a tailored Gradio Space for a Hugging Face LoRA.

Dev & Engineering

Hugging Face Spaces Builder

Build, deploy, debug, and maintain machine-learning apps on Hugging Face Spaces.

Data & Analysis

Hugging Face Dataset Explorer

Explore, query, and extract Hugging Face datasets through the Dataset Viewer API.

Dev & Engineering

Hugging Face Paper Research Assistant

Read AI papers and retrieve structured metadata from Hugging Face paper pages.

Data & Analysis

Hugging Face Local Evaluator

Run controlled inspect-ai or lighteval evaluations for Hugging Face Hub models on local hardware.

Data & Analysis

Trackio Experiment Tracking

Log, monitor, and query machine-learning experiments with dashboards, diagnostic alerts, and automation-ready output.

Data & Analysis

Hugging Face Vision Trainer

Train detection, classification, and segmentation models on Hugging Face Jobs GPUs and persist the results to the Hub.

Data & Analysis

Hugging Face Model Finder

Recommends AI models by task, benchmark performance, and available device memory.

Dev & Engineering

Hugging Face API Tool Builder

Turn Hugging Face API calls into reusable, composable command-line tools.

Automation & Ops

AWS Context Discovery

Resolve the active AWS environment before any account operation.

Automation & Ops

SageMaker Deployment Planner

Choose a practical Amazon SageMaker deployment path for your model, traffic pattern, and latency needs.

Automation & Ops

SageMaker Python Environment Setup

Build an isolated, version-aligned Python environment for SageMaker and AWS automation.

Data & Analysis

TRL Language Model Trainer

Train and fine-tune transformer language models with TRL’s CLI for SFT, preference alignment, and reinforcement learning.

Related skills