Storing general knowledge in VRAM has always been a dumb idea in the first place.

Qwen 3.8 27B beats Opus, Fable and GPT 5.6 by a comfortable margin on the AA-Omniscience Hallucination Rate benchmark.

It did OK on schlongbench v1.0 (test of a specific niche word that doesn't make it into smaller LLMs) but it sure does love to count words

https://pastes.io/r8F1AY8h

I do not rely on any LLM of any size for general knowledge baked into the weights, they all hallucinate and that is the wrong way to hold them imo

I think there is some merit in that smaller models cannot memorize so much of the training data, i.e. that they are less likely to do copyright infringement, and by analogy not having memorized SDK / API surfaces that have since changed from the training data