Spaces:

---

huggingface

/

HuggingDiscussions

like 73

Running

I think the tensor-core fp16 FLOPS should be used for GPUs supporting that. I note that V100 counts as way less than the theoretical 125 TFLOPS, listed e.g. here: https://images.nvidia.com/content/technologies/volta/pdf/tesla-volta-v100-datasheet-letter-fnl-web.pdf

Hey! Have you guys heard of LangFlow? It is a neat solution for developing AI-powered apps as well!

The GPU list is missing the RTX A4000 (16GB)

PR: https://github.com/huggingface/huggingface.js/pull/817

Would be nice to get ollama integration

https://github.com/LostRuins/koboldcpp for text
https://github.com/lllyasviel/Fooocus for image

I suggest adding Ollama as local app to run LLM's

I use GPT4All and it is not listed herein

Happy to submit a PR for the Ryzen AI Max 300 series (395 etc that powers the Framework Desktop), but first is it a CPU or a GPU? Or both?

It’s Both, eg Strix Halo is 395 as CPU and Radeon 8060S as iGPU with up to 128GB VRAM (unified)

Just a head's up, attempting to add hardware from available options within the dropdown list provides this error.

error '"[0].sku[2]" must be one of [B200, H200, H100, L40s, L40, L20, L4, GB10, RTX PRO 6000 WS, RTX PRO 6000 Max-Q, RTX 6000 Ada, RTX 5880 Ada, RTX 5000 Ada, RTX 4500 Ada, RTX 4000 Ada, RTX 4000 SFF Ada, RTX 2000 Ada, RTX A6000, RTX A5000, RTX A4000, RTX A2000, A100, A40, A10, A2, RTX 5090, RTX 5090 D, RTX 5080, RTX 5080 Mobile, RTX 5070, RTX 5070 Mobile, RTX 5070 Ti, RTX 5060 Ti, RTX 5060, RTX 4090, RTX 4090D, RTX 4090 Mobile, RTX 4080 SUPER, RTX 4080, RTX 4080 Mobile, RTX 4070, RTX 4070 Mobile, RTX 4070 Ti, RT…en 5 9000 (Ryzen 5), Ryzen Zen 4 7000 (Ryzen 9), Ryzen Zen 4 7000 (Ryzen 7), Ryzen Zen 4 7000 (Ryzen 5), Ryzen Zen 3 5000 (Ryzen 9), Ryzen Zen 3 5000 (Ryzen 7), Ryzen Zen 3 5000 (Ryzen 5), Ryzen Zen 2 3000 (Ryzen 9), Ryzen Zen 2 3000 (Ryzen 7), Ryzen Zen 2 3000 (Ryzen 5), Ryzen Zen 2 3000 (Ryzen 3), Apple M1, Apple M1 Pro, Apple M1 Max, Apple M1 Ultra, Apple M2, Apple M2 Pro, Apple M2 Max, Apple M2 Ultra, Apple M3, Apple M3 Pro, Apple M3 Max, Apple M3 Ultra, Apple M4, Apple M4 Pro, Apple M4 Max, Apple M5]'

Status
400
VersionHTTP/2
Transferred7.50 kB (3.43 kB size)
Referrer Policystrict-origin-when-cross-origin
Request PriorityHighest
DNS ResolutionDNS over HTTPS

I tried this on MacOS and Bazzite Linux, both on Firefox. It appears as if you've added the item and you can star it, but clicking away from the page causes it to disappear from the list. Please help, I want to add my new laptop :)

@driving-junk which hardware are you trying to add?

@kramp , I tried my m5 Macbook 32gb, an RTX 2070 and an AMD Ryzen 3000 era... same results for anything I tried.

Hi,

Missing from the hardware list:

• NVIDIA RTX™ 5000 Ada Generation Laptop GPU (16GB GDDR6) powers advanced AI with 682 AI TOPS
• Intel® Core™ i9 processor HX series (14th Gen)

Hey team, Merry Christmas! 🎄

A get a tiny bug on /settings/local-apps

• Hardware list doesn't persist after adding devices
• Page shows my hardware correctly but doesn't save to profile

Expected: auto-save on hardware addition
Actual: changes lost on page reload

Need VRAM estimation when browsing models!

EDIT: OK, I have the solution: delete everything and re-enter all informations...

Hey team, Merry Christmas! 🎄

A get a tiny bug on /settings/local-apps

• Hardware list doesn't persist after adding devices
• Page shows my hardware correctly but doesn't save to profile

Expected: auto-save on hardware addition
Actual: changes lost on page reload

Need VRAM estimation when browsing models!

EDIT: OK, I have the solution: delete everything and re-enter all informations...

Same here. Trying to add my chrismas presents to see if I can run a larger model, but I am left to do math with my fingers again 😀 . Happy new year!

Same workaround, had to remove everything and add it again.