Glad i could help ;)

You can get different results, sometimes better sometimes worse, most of the time differently phrased (e.g. the gemma models by google like to do bulletlists and sometimes tell me where they got that information from). There are models specifically trained / finetuned for different tasks (mostly coding, but also writing stories, answering medical questions, telling me what is on a picture, speaking different languages, running on smaller / bigger hardware, etc.). Have a look at ollamas library of models which is outright tiny compared to e.g. huggingface.

Also, i don’t trust OpenAI and others to be confidential with company data or explicit code snippets from work i feed them.

If you’re lucky you just set it to the wrong version, mine uses 10.3.0 (see below).

I tried running the docker container first as well but gave up since there are seperate versions for cuda and rocm which comes packaged with this as well and therefor gets unnecessary big.

I am running it on Fedora natively. I installed it with the setup script from the top of the docs:

curl -fsSL https://ollama.com/install.sh | sh

After that i created a service file (also stated in the linked docs) so that it starts at boot time (so i can just boot my pc and forget it without needing to login).

The crucial part for the GPU in question (RX 6700XT) was this line under the [service] section:

Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"

As you stated, this sets the environment variable for rocm. Also to be able to reach it from outside of localhost (for my server):

Environment="OLLAMA_HOST=0.0.0.0"

I have my gaming pc running as ollama host when i need it (RX 6700XT with rocm doing the heavy lifting). PC idles at ~50W and draws up to 200W when generating an answer. It is plenty fast though.

My mini pc home server is running openwebui with access to this “ollama instance” but also OpenAIs api when i just need a quick answer and therefor don’t turn on my pc.

I hope it went well :) i was completely ready to go back changing the image tag to v2 but didn’t need to.

Im so looking forward to this. When i tried to use tmpfs / ramdisk, the transcoding would simply stop because there was no space left.

Yes, since we have similar gpus you could try the following to run it in a docker container on linux, taken from here and slightly modified:

#!/bin/bash

model=microsoft/phi-2
# share a volume with the Docker container to avoid downloading weights every run
volume=/data

docker run -e HSA_OVERRIDE_GFX_VERSION=10.3.0 -e PYTORCH_ROCM_ARCH="gfx1031" --device /dev/kfd --device /dev/dri --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.4-rocm --model-id $model

Note how the rocm version has a different tag and that you need to mount your gpu device into the container. The two environment variables are specific to my (any maybe yours also) gpu architecture. It will need a while to download though.

Huggingface TGI is just a piece of software handling the models, like gpt4all. Here is a list of models officially supported by TGI, although they state that you can try different ones as well. You follow the link and look for the files section. The size of the model files (safetensors or pickele binaries) gives a good estimate of how much vram you will need. Sadly this is more than most consumer graphics cards have except for santacoder and microsoft phi.

I tried Huggingface TGI yesterday, but all of the reasonable models need at least 16 gigs of vram. The only model i got working (on a desktop machine with a amd 6700xt gpu) was microsoft phi-2.

I have a 5800X processor and 6700XT GPU which the site claims is barely ok. In reality my CPU is hardly ever doing anything when gaming while the GPU is at 100% usage all the time.

For a higher GPU, like the 7900XT (which i believe will have the power of a speculative 8800XT which i want to buy) the site claims the CPU to be the bottleneck.

Now i know that there is more to it than just the usage in the control center, but does this seem sketchy to someone else?

Meanwhile 4tb sata ssd is 300€ in germany

It’s true that you shouldn’t open ports to the internet. If you still want your services to be accessible from outside the local network you can install a wireguard server on your thin client that has access to the services you want. And if you really want to harden it you can restrict wireguard clients from ssh and other admin things.

You will need to open one port on the router to your wireguard server though. Wireguard is UDP though and ignores packages without an established connection, so attackers will not even know there is an open port on your router.

Edit: tailscale and zerotier are good external solutions to this as well without needing to open a port at all.

They have been built onto android until now, but i read that they wanted to ditch that and make their own os from scratch

TIL Amazon Echos can act as Zigbee hub. Still not using it lol.

Those examples you listed are not really modern imo. I’m not an UI/UX expert though.

I used Hugo to build my personal website. You can also easily build blogs with it. The difference to the usual approach is that you “code” the website in markdown which makes it super easy. Hugo then generates the html and css for you, which gets statically hosted. Check out the showcases and themes if you’re interested. I used a theme called papermod, it’s pretty common.

Finally, although I don’t think that this will have a meaningful outcome…

This is what i did. In europe, viable options start at 200€ on ebay (imo). If your use case outgrows one lenovo tiny (which is unlikely since you’re coming from a pi), you can buy more / other tiny pcs / a desktop pc / a server rack and put proxmox on everything for running services inside a cluster.

The most obvious answer. It is a little resource heavy though, so you would need at the very least a Pi 3, better a Pi 4.

Since gaming on linux has made ridiculous improvements im running it fulltime on my desktop machine. But I ran it on my laptops as sole OS for about 15 years now.

For router firmware i bought an archer c7 v5 last year (50€) and am running OpenWRT now. It’s sitting behind my ISPs router, but for that i don’t care.

Banking App would be really difficult since this is a huge security operation with liabilities. And discord would be nice to replace since it just fucks you and steals your data without giving it a second thought but there is no conpetitor i know of.

Because they are not publicly traded, i hope it stays that way