Thank you for this. my version was ghettofabulous and in the right direction but it appears the outputs are wrong.
ProllyInfamous 18 hours ago [-]
Be careful visiting this website: it is very dangerous to your wallet.
For example: just last month, it made me purchase a 5070Ti...
#GPUsAnonymous #Club1080Ti
ms7892 1 days ago [-]
Wow
not_your_vase 1 days ago [-]
That's not very accurate. It sees 8 GB RAM instead of 64. And it detects GTX 9 GPU, though I have an RTX30 one.
(Edit: now it came to my mind that Firefox has fingerprinting protection by default. But even after whitelisting this website, the result is the same)
embedding-shape 1 days ago [-]
I get "NVIDIA GeForce 8800" (?) in Firefox, and "ANGLE (NVIDIA Corpor" [sic] in Chromium/Chrome, the GPU is a RTX Pro 6000. I'm guessing if it doesn't have exact hit it basically picks at the top/bottom of the list?
kumarski 1 days ago [-]
see comment below from me.
egberts1 4 hours ago [-]
Ive got a tack server collecting dust.
How do I plug in a specific hardware?
jdiff 13 hours ago [-]
Be nice if I could correct the specs when detected incorrectly, or check the specs of a different machine without needing to physically pull this up on each machine.
Model choices all seem quite out of date. Phi-3, GPT-4o? Claude 3.5? And I thought Gemini Ultra was a subscription plan, not a model.
roboror 1 days ago [-]
Identified every component of my system incorrectly. W11.
spprashant 1 days ago [-]
For some reason it is not able to detect 64GB RAM on my Fedora Linux mini PC. It shows only 8GB.
majormunky 1 days ago [-]
Yeah, similar situation here, it shows 16gb on my 64gb mac
juancn 1 days ago [-]
It's too conservative, on my Air M4 I run gemma-4-12B-it-qat-UD-Q4_K_XL fine with llama.cpp
The app states "Small Models (1-3B)".
kumarski 1 days ago [-]
and no I'm not a software develpoer - just smacked it together with minimax for personal needs.
Thought it was nifty so shared. Would love to see a real CS person's version of this and/or best prompt to build something like this accurately and keep it up to date as models advance and SOTA shifts.
nottorp 1 days ago [-]
What about my desktop? Will it detect what models a desktop can run?
harvey9 1 days ago [-]
Reports android tablet as a 'linux PC'.
haeberli 1 days ago [-]
auto-detect failed to correctly detect 128GB ram vs 32GB ram on MacBook Pro M5
nickv 1 days ago [-]
Me too. I have the same spec model (M5 Max with 125gb of ram) and it reports as 32gb.
jrm4 1 days ago [-]
Interestingly wrong; probably has to do with the fingerprinting and whatnot.
I do appreciate that the "canirun" one
1) was also wrong
2) but let me pick my real card from the dropdown with results that seemed much more accurate.
Genuine question - is there literally any factor besides RAM and GPU (with VRAM info?)
efilife 1 days ago [-]
I recommend llmfit. It shows you exactly what models you can run and at what speeds
Firefox on macOS. site reported M1 and 16GB. Mac is M4 + 24GB
nailer 1 days ago [-]
Great idea! You're 95% of the way there and the rest is a couple of UI tweaks.
1. I thought the table showing a bunch of models after my laptop specs would be models I could run on my laptop.
Model Tier Example Models Params RAM Needed Your Status
Top SOTA GPT-4o, Claude 3.5 Sonnet, Gemini Ultra 1T+ Datacenter —
Large Models Llama 3 70B, Mistral Large, Command R+ 70B 64 GB Usable
Mid Models Llama 3 8B, Mistral 7B, Phi-3 Medium 7-13B 16 GB Usable
Small Models Phi-3 Mini, Llama 3 2B, Gemma 2B 1-3B 4 GB Your Tier
'Your tier' is too subtle. I would make 'Your tier' highlight the ENTIRE row in some bright color to make it more obvious, and maybe fade the other rows slightly.
2. I don't know what 'usable' means. How can these models be status:usable if they are not 'my tier'? I deduce 'usable' doesn't mean usable on my laptop but I don't know what 'usable' does mean.
3. Give me links to set up the best model I can.
kumarski 1 days ago [-]
Thank you G!
cyanydeez 1 days ago [-]
One word: wrong.
nailer 1 days ago [-]
This isn't constructive feedback. In my case it detected my Mac's capablities accurately and gave me models to use. What was wrong about it?
haeberli 1 days ago [-]
my case, did not detect my Mac's capabilities accurately
For example: just last month, it made me purchase a 5070Ti...
#GPUsAnonymous #Club1080Ti
(Edit: now it came to my mind that Firefox has fingerprinting protection by default. But even after whitelisting this website, the result is the same)
How do I plug in a specific hardware?
Model choices all seem quite out of date. Phi-3, GPT-4o? Claude 3.5? And I thought Gemini Ultra was a subscription plan, not a model.
The app states "Small Models (1-3B)".
Thought it was nifty so shared. Would love to see a real CS person's version of this and/or best prompt to build something like this accurately and keep it up to date as models advance and SOTA shifts.
I do appreciate that the "canirun" one
1) was also wrong 2) but let me pick my real card from the dropdown with results that seemed much more accurate.
Genuine question - is there literally any factor besides RAM and GPU (with VRAM info?)
https://github.com/AlexsJones/llmfit
1. I thought the table showing a bunch of models after my laptop specs would be models I could run on my laptop.
'Your tier' is too subtle. I would make 'Your tier' highlight the ENTIRE row in some bright color to make it more obvious, and maybe fade the other rows slightly.2. I don't know what 'usable' means. How can these models be status:usable if they are not 'my tier'? I deduce 'usable' doesn't mean usable on my laptop but I don't know what 'usable' does mean.
3. Give me links to set up the best model I can.