Is it still telling people to put glue on their pizza and convincing teenagers to kill themselves?

• approach one: pay attention and credit new or improved architecture designs and research.
• approach two: spend more attention on benchmarks. especially specific benchmarks ( that are not focused with industrial domain tasks.) **domain task pursuit, is useful!.. but it depends on if your interest align to popular domains.
• approach three: if willing to utilize remotely hosted models. rating should also take in consideration.. tools and everything else: websearch performance, RAG performance, smooth interface, pref/balance between speed vs comprehensiveness, cost (if relevant), etc.. .

I posted link below to example where they fine tuned model ( take it like a employee training ) for specific task.

• i admit benchmarks are well designed to objectively measure competence on challenging problems that require skill and really need only ONE correct answer.

The AI Efficiency Index tracks the cost/intelligence mix. Low intelligence is useless. Capability scales exponentially. Expensive ≠ better value. MiMo-V2.5 is the leader.

If you have any questions feel free to ask. This uses the Artificial Analysis leaderboard. They have "cost per task" which I think is weird.

But it's better to use faster models for this type of hardware anyway. The MoE type of models (such as 26B A4B, or 35B A3B) are vastly, vastly faster for normal usage, but they are a bit worse in some cases. Also Googles QAT trained model versions also have less RAM requirements without losing much quality.

I'm just saying that, so others are not discouraged too much. It's not the same experience as the full version off course, but you can use them with some tricks on weak hardware too.