I actually enjoy retro gaming. Earthbound and mother 3 are my favorite games! The professor Layton serie is also great! The thing is, while retro games are a huge source of “free” games, they’re often too hard. I also found myself falling in a rabbit hole with an entire generation of retro games that nobody cares about anymore despite being full of great games : flip phone java games" (j2me). I highly recommend trying them if you want to play games on your phone without being thrown a billion ad and microtransactions. Just play the touchscreen variants and your golden. Some good games are : doom RPG 2 and Wolfenstein RPG, literally any game by digital chocolate.

thanks a lot for recommandation, sea of stars and pizza tower look 👌! and yeah my machine isn’t capable to run bigger 3d games. Lol.

Rpg or platformer.

The only way I can access games is by pirating them and I don’t pirate indie games unless they already pretty successful and it wouldn’t hurt them. Yeah, even that 2.99$ is too much when you live in shitty third world country.

Tried braid and got bored real quick.

Tried fez and didn’t even continue past the first 30 min

Tried Undertale, but basically knew the story already from spoilers, and it was kinda boring, uninteresting and too hard.

Played Crashlands and it was a grindfest that actually made me relieved that I finished the game, only to discover it was planet 1 of 3. 👉Uninstalled.

Really enjoyed fear and hunger despite being shit at the game and ended up just cheating. (Was still freaking hard 😭)

Finished and enjoyed Limbo.

I just want a game with a great story, a gameplay with medium low difficulty that isn’t a grindfest and isn’t too long ( usually caused by the endless grinding).

This is stupid cause it will simply cause Firefox to be banned. The devs should just host it somewhere else and teach the user to run external extensions.

If you guys like hiking and stuff, there’s this cool open source app called trail sense on f-droid and it’s just so much feature packed…

I don’t hike, so I only use it for it’s pedometer capabilities and a hypothetical situation where “I might get really lost” but the amount of features it has for hiking and survival is crazy and so I think deserves to be more known.

My fucking dumbass created a keyloger in python in a few hours by exploiting a unfixed bug in windows 10 and it took 3 days for windows defender to flag it as a virus.

I had a hunch that writing the actual Upload/download speed tather than mbps was probably wrong. My bad, my internet provider lingo is rusted.

I don’t have a jellyfin server but 1MB/s (8mbps) for each person watching 1080p (3.6Gb per hour of content for each file) seems reasonable. ~3MB/s (24mbps) upload and as much download should work.

Ad and seo Spam&Scam websites aggregator*

No. Quantization make it go faster. Not blazing fast, but decent.

Completely forgot to tell you to only use quantized models. Your pc can run 4bit quantized versions of the models I mentioned. That’s the key for running llms on at consumer level hardware. You can later read further about the different quantizations and toy with other ones like Q5_K_M and such.

Just read phi-3 got released and apparently it’s a 4B that reach gpt 3.5 level. Follow the news and wait for it to be add to ollama/llama.ccp

Thank you so much for taking the time to help me with that! I’m very new to the whole LLM things, and sorta figuring it out as I go

I became fascinated with llms after the first AI booms but all this knowledge is basically useless where I live, so might as well make it useful by teaching people what i know.

The key is quantized models. A full model wouldn’t fit but a 4bit 8b llama3 would fit.

Yeah, it’s not a potato but not that powerful eaither. Nonetheless, it should run a 7b/8b/9b and maybe 13b models easily.

running them in Python with Huggingface’s Transformers library (from local models

That’s your problem right here. Python is great for making llms but is horrible at running them. With a computer as weak as yours, every bit of performance counts.

Just try ollama or llama.ccp . Their github is also a goldmine for other projects you could try.

Llama.ccp can partially run the model on the gpu for way faster inference.

Piper is a pretty decent very lightweight tts engine that can be directly run on your cpu if you want to add tts capabilities to your setup.

Good luck and happy tinkering!

Specs? Try mistral with llama.ccp.

It shouldn’t happen for a 8b model. Even on CPU, it’s supposed to be decently fast. There’s definitely something wrong here.

Sadly, can’t really help you much. I have a potato pc and the biggest model I ran on it was Microsoft phi-2 using the candle framework. I used to tinker with Llama.cpp on colab, but it seems they don’t handle llama3 yet. ollama says it does , but I’ve never tried it before. For the speed, It’s kinda expected for a 70b model to be really slow on the CPU. How much slow is too slow ? I don’t really know…

You can always try the 8b model. People says it’s really great and even replaced the 70b models they’ve been using.

Run 70b llama3 on one and have a 100% local, gpt4 level home assistant . Hook it up with coqui.Ai xttsv2 for mind baffling natural language speech (100% local too ) that can imitate anyone’s voice. Now, you got yourself Jarvis from Ironman.

Edit : thought they were some kind of beast machines with 192gb ram and stuff. They’re just regular middle-low tier pcs.

New browser engines already exists : servo ( rust), Ladydbird (C++) are actively being developed. Both are still far from being daily driveable, but considering mozilla is apparently shiting the bed it’s better than nothing.

An accessibility first OS with a 100% local, low requirement LLM such as Microsoft phi-2 (fine-tuned for API calls ) would definitely be great.

I’ve been reading norse mythology so i geuss Odin would be a fitting name for such OS.

innovation