~/runthismodel
daemon okbuild 5a3c91d00:00:00Z

Uncensored chat & assistant models

Refusal-removed general LLMs — abliterated, Dolphin, and natural base models

Local LLMs without the 'I can't help with that' reflex. Includes mlabonne abliterations (refusal-direction ablation, no retraining), Cognitive Computations Dolphin fine-tunes, and official base models that were never RLHF-aligned. Read each model's license — some inherit Llama Community terms.

  1. 1

    Cognitive Computations

    Dolphin Mistral 24B (Venice Edition)

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

    24B14.9 GB
  2. 2

    Cognitive Computations

    Dolphin 3.0 R1 Mistral 24B

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

    24B13.85 GB
  3. 3

    mlabonne

    NeuralDaredevil 8B (abliterated)

    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.

    8B5.08 GB
  4. 4

    Cognitive Computations

    Dolphin 3.0 Llama 3.1 8B

    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.

    8B5.08 GB
  5. 5

    mlabonne

    Llama 3.1 8B Instruct (abliterated)

    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.

    8B5.08 GB
  6. 6

    mlabonne

    Llama 3.1 70B (lorablated)

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

    70B40.1 GB
  7. 7

    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.

    8B5.3 GB
  8. 8

    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.

    12B7.7 GB

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