Pure big AI (OpenAI, Anthropic) companies are so cooked, small models are coming to eat their lunch. Meta, Google et.al. have other arrows in their quiver. Even IBM are likely too big, Qwen 3.8 27B is a beast you can host on a gaming rig and suitable for many, many use cases.
Pure big AI (OpenAI, Anthropic) companies are so cooked, small models are coming to eat their lunch. Meta, Google et.al. have other arrows in their quiver. Even IBM are likely too big, Qwen 3.8 27B is a beast you can host on a gaming rig and suitable for many, many use cases.
Have you gotten any good use out of local models personally?