only open local models are suitable for “companions”. Anyone who can be sued cannot risk not “covering their ass legally” responses, which prevents “engagement with casual steering away from (self) harm” while staying in character, instead of corporate’s legal department mandate of a textbook response that makes the user find a better AI girlfriend.
I mean sure if your older machine’s newer GPU has 200 GB of VRAM to run a decent quant… Fucking hell just Q4 is around 100 gigs and then you’d want a decent amount of KV cache too.
It doesn’t. Use Strata to run it. Choose the recommended settings it gives you during the install. People can run it with 12GB of VRAM and 32GB of system RAM. It partially loads the most common parts of the model I’m VRAM and swaps from RAM when needed. Rarely it needs to grab from the SSD, but it’s swapping while processing so it doesn’t seem slow at all. I get around 60-80 tokens per second on average. 16GB VRAM and 48GB RAM.
I get where you are coming from. I thought it would run slow AF as well before I tried it. 😄
Mostly Chinese companies that aren’t necessarily required to generate infinitely compounding profits just to continue existing.
Edit: Also third parties such as volunteers who fine tune models for specific purposes. Just like with all software - everyone can learn and contribute when it’s open source.
Many groups are making models now. I see a future where we have open source data sources, models, and weights. Niche groups can extend models to be trained on whatever they want.
I just got Qwen 3.8 Flash Next running locally. It’s damn good on an older machine with a newer GPU. Local LLMs should scare them the most.
only open local models are suitable for “companions”. Anyone who can be sued cannot risk not “covering their ass legally” responses, which prevents “engagement with casual steering away from (self) harm” while staying in character, instead of corporate’s legal department mandate of a textbook response that makes the user find a better AI girlfriend.
I mean sure if your older machine’s newer GPU has 200 GB of VRAM to run a decent quant… Fucking hell just Q4 is around 100 gigs and then you’d want a decent amount of KV cache too.
I encourage you to give Qwen 3.8 flash next a try. It’s amazing what a typical gaming machine can do with it.
I read it needs 75gb at the minimum quantization? It doesn’t seem “typical gaming machine”
It doesn’t. Use Strata to run it. Choose the recommended settings it gives you during the install. People can run it with 12GB of VRAM and 32GB of system RAM. It partially loads the most common parts of the model I’m VRAM and swaps from RAM when needed. Rarely it needs to grab from the SSD, but it’s swapping while processing so it doesn’t seem slow at all. I get around 60-80 tokens per second on average. 16GB VRAM and 48GB RAM.
I get where you are coming from. I thought it would run slow AF as well before I tried it. 😄
Yeah but who’s making the models?
Mostly Chinese companies that aren’t necessarily required to generate infinitely compounding profits just to continue existing.
Edit: Also third parties such as volunteers who fine tune models for specific purposes. Just like with all software - everyone can learn and contribute when it’s open source.
Many groups are making models now. I see a future where we have open source data sources, models, and weights. Niche groups can extend models to be trained on whatever they want.