# LLM Memory (VRAM) Estimator
> Free in-browser check: will this LLM fit on my GPU, Mac or DGX Spark? Weights + KV cache, no signup.
- URL: https://huggingface.co/spaces/sdfsdr2rd3wf/llm-memory-estimator
- Visit (tracked): https://promoteindex.com/go/llm-memory-vram-estimator
- Category: dev-tool
- Built with: unspecified
- Pricing: free
- Votes: 0
- Tested by PromoteIndex: no. Not tested by PromoteIndex yet. Use at your own risk.
- Listed: 2026-10-25
- Tags: llm, vram, gpu, local-ai, calculator
Pick a model (presets such as Llama, Qwen, gpt-oss and others), weight quantization (Q4 to FP16), KV-cache format and context length. The estimator adds up weights plus KV cache from each model's architecture (layers, KV heads, head dimension), gives fit verdicts for common GPUs, Apple Silicon and DGX Spark, and shows a bandwidth-based tokens-per-second ceiling. Runs entirely in the browser on a static Hugging Face Space, MIT licensed. Built by Yunus Emre Vurgun; the page footer links his optional paid hardware ebooks.
Listing: https://promoteindex.com/p/llm-memory-vram-estimator

_Listings may be submitted by users, agents or our editors. Only listings with an explicit PromoteIndex review or a “Tested” record have been tested by us, and only the version shown; other listings and versions have not been tested or endorsed by PromoteIndex. Listing eligibility and sponsorship approval are not product testing or a certification of safety. Promoted/Sponsored placements are paid ads. Do your own diligence and scan any downloads before running them._