Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.

🌆 Utilities for handling monitors, resolutions, wallpapers and timed wallpapers + display available VRAM

MacOS menu‑bar utility to adjust Apple Silicon GPU VRAM allocation

Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.

Social AI Agent Blueprint. Powered by vram.ai

Virtual Machine with a 240x160 VRAM display.

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

Calculate VRAM requirements for running Large Language Models (LLMs) and recommends suitable GPUs based on your needs

Rust block device in userspace

Texture group flush/fetch manager for GameMaker Studio 2.3

Know your VRAM before you run. Instant GPU memory estimates for any HuggingFace model.

Run any large transformer model on consumer GPUs. No quantization. No compromise.

CLI tool to check GPU VRAM before loading AI models. Prevent OOM crashes.

Find which LLMs actually fit on your hardware. Client-side GPU detection, quantization-aware memory estimation, and speed predictions.

Dynamic VRAM allocation manager for the PSP

Vram memory usage estimation for GameMaker

Diamond Monster 3D 3Dfx Voodoo 1 VRAM Expansion Mod up to 8MB

A VRAM Expansion Board for the Compaq S3 Virge GX & Matrox Mystique 220 Video Card

Compare API providers, local GPUs, and cloud for any model

Plug-and-play homelab dashboard in one container — GPU, local-AI model VRAM, Docker, systemd and host health. One page, no Prometheus/Grafana.