Uncensored & Abliterated AI Models

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.

Eric Hartford's flagship uncensored fine-tune of Llama 3.1 8B. Steerable assistant with personality controls and no built-in refusals — strong general-purpose pick at 8B.

Official Mistral-Nemo 12B foundation model (NVIDIA collab) — pretrained only, no instruct or refusal layer. Naturally uncensored, Apache 2.0, 128K context.

Llama-3 8B with refusal direction ablated, then DPO-recovered to restore capability. Best quality-retention 8B abliteration — minimal regression vs the official Instruct model.

Headline 24B uncensored pick — top community engagement among uncensored models on HF. Steerable assistant on Mistral-Small-24B base. Apache 2.0.

Long-running 8B roleplay reference. Trained for character voice consistency and long-form creative writing. CC-BY-NC-4.0 — non-commercial use only.

Mistral Codestral with refusal direction ablated. Code-specialized model without the 'I can't help with that' filter. Inherits Codestral's non-commercial license.

Top-of-line 24B roleplay model, Mistral-Small-3.2-24B base. Active development cycle — TheDrummer ships frequent revisions tracking the latest base models.

Pure refusal-direction ablation of Llama-3.1-8B-Instruct. No retraining — keeps the official instruct behavior but removes the 'I can't help with that' reflex.

31B creative-writing model — sweet spot between 24B and 70B. Built on Mistral-Small-3.1 upscaled. Strong long-context narrative generation.

Canonical 70B creative-writing and roleplay model. Llama-3.3-70B base with extended training on long-form prose. The reference 70B uncensored pick.

Only widely-available uncensored R1-style reasoning model. Mistral-Small-24B base with chain-of-thought training and refusals removed. 128K context.

Qwen2.5-72B fine-tuned on Claude-Opus-style literary data. Highest-quality long-form prose at the 72B class. Apache 2.0.

Mistral-Nemo-12B fine-tuned on curated Claude-style prose data. Built for long-form creative writing with literary register.

Newest Rocinante release — 16B upscaled Mistral-Nemo for richer prose at the 12-16GB tier. Recent (2026) release, smaller community footprint but actively developed.

Mistral-Nemo-12B roleplay fine-tune optimized for character chat. Stable workhorse for the 12GB tier — strong dialog, low repetition.

Llama-3.1-70B-Instruct with abliteration applied via LoRA merge. Cleanest 70B refusal-removed pick — keeps the official Instruct quality.

Mistral-Small-22B base, Anthracite's Claude-style prose training. Sits between 12B and 70B — for users who want Magnum quality on a single 24GB card.