Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.
Use your NVIDIA GPU's VRAM as swap space on Linux. Built for laptops with soldered memory and no upgrade path. If you have an RTX card sitting there with 8GB of VRAM and you're getting swapped to SSD, this puts that VRAM to work
MacOS menu‑bar utility to adjust Apple Silicon GPU VRAM allocation
Plug-and-play homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, host health. Built-in read-only MCP server so AI agents can explore it too.
Social AI Agent Blueprint. Powered by vram.ai
First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.
Find local AI models for your GPU. Open-source VRAM, quantization and speed estimates in your browser — no install or sign-up. 한국어·English.
Hardware-accelerated Linux kernel block driver and multi-tier memory cascade (ZRAM ➔ PCIe VRAM ➔ NVMe). Opportunistically leases idle GPU memory as a zero-allocation, revocable swap cache with sub-millisecond latency, zero SSD wear, and crash-safety on Linux & WSL2.
Local AI for your whole house: chat, images and voice on your own GPU. Computes each model's flags, fits them to your VRAM, and hot-swaps them behind one OpenAI- and Anthropic-compatible API.
Rust block device in userspace
Detect and work around silently-corrupting VRAM on consumer GPUs. No ECC, no page retirement, no error - the driver just returns wrong data.
The local-inference observability layer for your terminal: live tokens/sec, VRAM-spill & throttle warnings, the GPU metrics nvidia-smi can't show. Also a gorgeous htop/btop-class system monitor. Rust, zero deps.
Find which LLMs actually fit on your hardware. Client-side GPU detection, quantization-aware memory estimation, and speed predictions.
Fixes the VRAM crashes, missing icons and mushy textures in Assetto Corsa EVO.
To associate your repository with the vram topic, visit your repo's landing page and select "manage topics."