What LLM fits my GPU? VRAM index for 117 models
quantized.uk- Category
- AI Tools
- Rank
- No. 3547Tools index
- Type
- TOOL
- Date
About
A web index that lets you pick a GPU, Mac or CPU RAM size and see which quantized LLMs fit, with the memory maths behind each estimate and a command to run it. Sizes are computed at 4K context and batch 1 from weights, KV cache and a 10% activation allowance. This helps choose a model and quantization level before downloading it.
Why it made the leaderboard
Pick a GPU or Mac and see which quantized models fit, with VRAM estimates (weights, KV cache, activations at 4K context) and run commands, so you avoid trial-and-error downloads.
Tags
llmvramquantizationgpugguflocal-llm
Media
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.