Lol, there are smaller versions of Deepseek-r1. These aren’t the “real” Deepseek model, but they are distilled from other foundation models (Qwen2.5 and Llama3 in this case).

For the 671b parameter file, the medium-quality version weighs in at 404 GB. That means you need 404 GB of RAM/VRAM just to load the thing. Then you need preferably ALL of that in VRAM (i.e. GPU memory) to get it to generate anything fast.

For comparison, I have 16 GB of VRAM and 64 GB of RAM on my desktop. If I run the 70b parameter version of Llama3 at Q4 quant (medium quality-ish), it’s a 40 GB file. It’ll run, but mostly on the CPU. It generates ~0.85 tokens per second. So a good response will take 10-30 minutes. Which is fine if you have time to wait, but not if you want an immediate response. If I had two beefy GPUs with 24 GB VRAM each, that’d be 48 total GB and I could run the whole model in VRAM and it’d be very fast.

They’re probably referring to the 671b parameter version of deepseek. You can indeed self host it. But unless you’ve got a server rack full of data center class GPUs, you’ll probably set your house on fire before it generates a single token.

If you want a fully open source model, I recommend Qwen 2.5 or maybe deepseek v2. There’s also OLmo2, but I haven’t really tested it.

Mistral small 24b also just came out and is Apache licensed. That is something I’m testing now.

Most open/local models require a fraction of the resources of chatgpt. But they are usually not AS good in a general sense. But they often are good enough, and can sometimes surpass ChatGPT in specific domains.

https://sh.itjust.works/c/localllama

Word can in fact open odt files. It was added quite a long time ago. Don’t know how good the compatibility is, though

I use Simple Login a lot too. But be careful, as some sites reject these email addresses. Or in the case of Shell Recharge, change their business logic to reject the email addresses without letting me change to another email … Haven’t been able to log in for months 🙃

It’s because OsmAnd has some serious issues searching for certain addresses. It’s not an OpenStreetMaps problem, but an issue with the app. Organic Maps is better. Magic Earth is even better. Note: only talking about address searching. OsmAnd still has a ton of other useful features.

If I need to use OsmAnd, sometimes I’ll copy the plus code from Google Maps, as that translates to GPS coordinates.