Naturally uncensored base models

Official foundation models with no instruct or RLHF alignment

Pretrained-only models from Mistral, Qwen, and Meta — no abliteration needed because alignment was never applied. Closer to the raw distribution; less assistant-shaped, more open-ended. Best for researchers and for fine-tuning your own assistant.

1
Alibaba
Qwen3 8B Base
Official Qwen3 8B foundation model — pretrained only, no RLHF or refusal training. The 'naturally uncensored' option: no abliteration needed because alignment was never applied. Apache 2.0.
8B≥ 5.3 GB
2
Mistral AI
Mistral Nemo Base 12B
Official Mistral-Nemo 12B foundation model (NVIDIA collab) — pretrained only, no instruct or refusal layer. Naturally uncensored, Apache 2.0, 128K context.
12B≥ 7.7 GB

Not sure which fits your machine? Auto-detect your hardware →