Yes. You can use opencode, the agenetic coding tool, with just about any llm runner or model. But Opencode Go is their cloud-llm suscription plan, with limited/slightly-dated llm models.

Good thinking to mention open-webui - I was only thinking agenetic coding, but I use open-webui for llm chatting. I think it’s fantastic.

FYI, I think opencode go is kind of a subscription model, not a direct credits-to-tokens model. In terms of value it’s nowhere near as good as Claude’s subscriptions, but it seems way more valuable that paying for tokens directly. However they only offer a few models - decent ones, but not many and a little behind the times.

AMD Ryzen 9 9950X CPU and AMD radeon pro w7900 (48GB vram). I get 55tps output pretty consistently, but ingesting context starts around 1500tps and if context size reaches, say, 50K, tps drops to around 200tps. I often have to wait a bit, but it’s a price I’m happy to pay for local-only AI

I use opencode with locally-hosted llama.cpp - usually with qwen3.6-35b-a3b.

I tried opencode go for a couple month, and its definitely nice to have an lln runner with more gram and more GPUs, but I prefer to have all my stuff local whenever it’s possible. Also, I’d use up my token allotments fairly quickly on opencode go.

I also tried opentouter and it, too, was great - many more models. But I exhausted by credits even quicker than opencode go, and its also not local.

Very good points.

That’s hot, and climate change exists. I get it. But 48C (118F) shutting things down? I used to live in Palm Springs, CA where it’s over 37F for 5-6 months every year, and the hottest I personally experienced was 51C (124F) and I experienced a lot of 47C - and while that was indeed unpleasantly hot (but it’s a dry heat! 🙂), life continued as normal. I remember even seeing tons of laborers building new houses mid day as a regular occurrence.

A more apt post for this community might be to suggest alternatives to a Google app/service, rather then how to continue using it.

I share your frustration. Both of my parents have multiple sheets of paper next to their computers with “all” of their passwords written on them, but when they need tech support (i.e., me), the password they need is never on there.

Have you considered the possibility that this could be a subconscious act by your mom to communicate with you, a way to ensure she gets to talk to you more frequently than otherwise?

The only thing “missing” from Mullvad is port forwarding, but I run qbittorrent constantly and have no problems. Not sure how Port forwarding helps torrents, but I don’t seem to need it.

It does seem like what I’m seeing would be someone’s idea/joke of a drunk mode, but it’s how the page loads for me - I didn’t click anything. And I can’t read the buttons to see if one days “turn off drunk mode”.

Holy shit how can you read that? For a minute I thought the text was encoded until maybe I clicked a button, then I thought it might be Arabic, now I see that’s it’s English but I can’t even make out all the letters. No thanks.

Their whole life.

Not my GPU. I have an AMD.

Requirements

• NVIDIA Ampere or newer GPU (A100, H100, H200, B200, RTX 3000+)

I now see that I expressed my idea unclearly. Sorry!

I don’t have any RSS feeds specifically for new/good apps. I meant that in my normal RSS feeds, sometimes new/good apps are mentioned that I want to take a look at.

I get leads from sites like selfh.st, Lemmy communities that discuss FOSS or Linux (or even non-tech-related communities sometimes mention an app that has to do with their domain of interest), and I sometimes search github (FYI, I use github as little as possible - I host my own Forgejo forge for my stuff - but, like Youtube, you have to go where the data is if you’re going to find the data).

I use Obtainium. It’s not a store or repo, so I have to manually find the apps I want to install. I even prefer it over fdroid: I might search for apps on fdroid but then go to the app’s repo (on codeberg or github, etc) and try to install them via Obt ainium. But 98.6% of the time, I don’t use fdroid to search for apps - I find them mentioned on Lemmy, in my RSS feeds, searching the internet via searxng.

I’m pretty sure he knew why.

I’m my experience, running Ollama locally works great. I do have a beefy GPU, but even on affordable consumer grade GPUs you can get good results with smaller models.

So it technically works to run an AI agent locally, but my experience has been that coding agents don’t work well. I haven’t tried using general AI agents.

I think the amount of VRAM affordable/available to consumers is nowhere near enough to support a context length that’s necessary for a coding agent to remain coherent. There are tools like Get Shit Done which are supposed to help with this, but I didn’t have much luck.

So I’m using OpenCode via OpenRouter to use LLMs in the cloud. Sad that I can’t get local-only to work well enough to use for coding agents, but this arrangement works for me (for now).

Double upvote!

Rules 1, 2 and 6