Right-sizes LLM models to your system's RAM, CPU, and GPU

Re:Right-sizes LLM models to your system's RAM, CPU, and GPU by ff00 on Monday March 02, 2026 @01:35AM (#47214578)

Found this website, not tested https://www.caniusellm.com/

[ Parent | on HN ]

Re:Right-sizes LLM models to your system's RAM, CPU, and GPU by onion2k on Monday March 02, 2026 @01:46AM (#47214637)

That site says my 24GB M4 Pro has 8GB of VRAM. Browsers can't really detect system parameters. The Device Memory API 'anonymizes' the value returned to stop browser fingerprinting shenannigans. Interesting site, but you'll need to configure it manually for it to be accurate.

[ Parent | on HN ]

Re:Right-sizes LLM models to your system's RAM, CPU, and GPU by Hamuko on Monday March 02, 2026 @02:30AM (#47214867)

You have a whole 8 GB of VRAM? My 32 GB M1 Max has 8 GB of RAM and ~4 GB of VRAM according to this website.

[ Parent | on HN ]

Re:Right-sizes LLM models to your system's RAM, CPU, and GPU by onion2k on Monday March 02, 2026 @02:37AM (#47214922)

You have 32GB of unified ram. It's not split between RAM and VRAM. The website cannot tell this using the browser's APIs.

[ Parent | on HN ]

Re:Right-sizes LLM models to your system's RAM, CPU, and GPU by fwipsy on Monday March 02, 2026 @01:41AM (#47214611)

Seems broken. When I changed my auto-detected phone specs to manually entered desktop specs the recommendations didn't change at all.

[ Parent | on HN ]