qwen-3.6 is really interesting. The dense 27B model is pretty slow for me whereas the sparse 31B is blazingly fast but it also needs to be since it's so chatty. It produces pages and pages of stream of consciousness stuff. 27B does this to a lesser extent but slow enough that I can actually read it whereas 31B just blasts by.
I haven't yet compared either to Gemma 4. I tried that out the day after it came out with the patched llama.cpp that added support for it but I couldn't make tool calling work and so it was kind of useless. I should try again to see if things have changed but judging by what people say, qwen-3.6 seems stronger for coding anyway.
I found that you can run models locally pretty well that exceed your VRAM by a bit. At least ollama will hand excess off to your system RAM. Maybe performance suffers but I've never actually seen it crap out and I can wait a few minutes for a response.
I don't remember exactly in which book's introduction Hannah Arendt mentioned this, but she pointed out that every time humanity learned a new skill that improved its efficiency in some capacity, that skill as well as adjacent skills diminished irrevocably.
AI is the thing that for the first time can think better than us (or so at least some people believe) and is seen as an efficiency booster in the world of cognition and ideas. I'd think Hannah Arendt would be worried with what we are currently seeing and where we might be headed.
I haven't yet compared either to Gemma 4. I tried that out the day after it came out with the patched llama.cpp that added support for it but I couldn't make tool calling work and so it was kind of useless. I should try again to see if things have changed but judging by what people say, qwen-3.6 seems stronger for coding anyway.