This is very helpful too: https://www.canirun.ai/

embedding-shape 3 hours ago | parent | next [-]

Love that it defaults to the GPU being "NVIDIA GeForce 8800 GTX", a GPU released in 2006 with ~700MB of VRAM...

The estimates seems far off as well, took https://www.canirun.ai/model/gpt-oss-120b as an example, with a RTX Pro 6000 and every single number is off, and notably misses estimation for the most important quant for GPT-OSS, the MXFP4 variant.

▲

kilroy123 2 hours ago | parent | prev | next [-]

Yes, I really like this site too, but it's a bit outdated.

"39d ago" in AI time is like 1 year outdated info.

	▲	nullsanity 39 minutes ago \| parent [-]
		[dead]

▲

schaefer an hour ago | parent | prev | next [-]

> canirun.ai

I run dgx spark, and the results here are soooo incomplete for my platform that I can’t trust this site (for my usecase).

	▲	nullsanity 40 minutes ago \| parent [-]
		[dead]

▲

freeCandy 3 hours ago | parent | prev [-]

Every browser gives me a different result, I guess I can't blame the site for that. But it should perhaps mention which browser would be the most accurate.