Quantized is a VRAM index that answers the question of what LLM fits your GPU. You pick a card, from an RTX 5090 with 32 GB down to older Tesla and Mac configurations, and see which of 123 models fit, with the measurements taken on real hardware. The site also carries a quant hub, GPU listings, benchmarks, a cookbook and tools.
Be the first to rate Quantized VRAM Index. Your feedback helps other users decide.
Select your exact card and memory configuration to filter the model list.
See measured VRAM requirements instead of estimated ones.
Use the quant hub and cookbook to weigh quality against memory.
Similar tools in the same category โ compare side-by-side
Rivinci runs both sides of a business AI: the chatbot that talks to people and the MCP servers that ...
Nysa is shared memory for teams that work with AI agents. Your agents start every conversation from ...
Ida is a voice layer for your Mac: you say it and Ida gets it done. It performs voice actions that w...
Guides and comparisons about productivity tools
Eight launches on the boundary between agents and the world: WebMCP for websites, business chatbots with tools, deterministic facts and diagrams as text.
A free AI toolkit for students: research, note-taking, writing, math, coding, and study aids, with the honest limits of each free plan.
How email marketing automation uses AI in 2026: segmentation, dynamic content, send-time prediction, and drafting, and which parts still need a human.
A practical AI marketing stack for small businesses: Rytr for copy, Canva AI for design, Gamma for decks, VEED.io for video, and free options to start.
A practical plan for automating customer service: draft replies, summarize threads, triage tickets and wire autonomous agents, without losing human oversight.