
Hf mem
SkillEstimate GPU memory for a Hugging Face model's weights and KV cache without downloading it
- Open source
- 11.4K GitHub stars
- AI models and LLM tooling

Estimate GPU memory for a Hugging Face model's weights and KV cache without downloading it

Recommend top Hugging Face models for a task from official leaderboards and device limits

Run local evals on Hugging Face models with inspect-ai or lighteval and pick a backend

Explore Hugging Face datasets through the read-only Dataset Viewer API

Build Gradio web UIs, chatbots and ML demos in Python, and call Spaces from the CLI

Fine-tune LLMs with TRL or Unsloth on Hugging Face Jobs GPUs and convert to GGUF

Find GGUF models on Hugging Face, pick a quant and serve them locally with llama.cpp

Lets an agent create, list, update and delete Arize AI LLM provider integrations

Lets your agent manage Arize annotation configs, review queues and span labels

Generates a prompt that makes the agent find representative code exemplars in a codebase

Guides an agent to build an llms.txt index file for a repository from its structure

Guides building C#/.NET MCP servers and clients on the current ModelContextProtocol 2.x

Guides an agent through building LLM eval pipelines with datasets, evaluators and pixie

Polishes a prompt file's structure, wording and grammar for end users

Registers prompt-based agents in Azure AI Foundry from a local JSON manifest

Generates images from text prompts via OpenAI or Google Gemini image APIs

Scaffolds a Java MCP server with the MCP Java SDK 2.x, tests and client config

Generates and edits images through OpenRouter's Gemini 3 Pro Image model

Guides agents through debugging LLM apps with Phoenix traces, datasets and experiments

Guides building, running and validating LLM evaluators with the Phoenix framework

Scaffolds a PHP MCP server project with tools, resources, prompts and PHPUnit tests

Turns rough ideas and drafts into finished, copy-ready prompts for chat LLMs

Generates a Rust MCP server project with tools, prompts, resources and tests via rmcp

Turns Copilot customization files, MCP server docs or URLs into concise tldr-style

Keeps a repository's llms.txt file in sync with docs and spec changes

Adds policy checks, intent screening, trust scores and audit logs to AI agents

Guides agents through self-critique, reflection loops and LLM-as-judge evaluation

Reviews a prompt for safety, bias, security and effectiveness, then suggests a rewrite

Guides agents to current official OpenAI docs, model choices and model upgrades

Compiles, benchmarks and packages LiteRT models for Google Tensor Pixel TPUs