Uncensored AI guide
VIDEO COMPANION GUIDE · NOVEMBER 2026

The best uncensored AI
for every hardware tier.

The video companion guide: every model from the video, from a phone to a GPU cluster, with model pages and step-by-step PocketPal and Hermes setups.

Sources checked November 18, 2026Hardware advice is estimated
BEFORE YOU START

This page goes with the video. Pick the tier that matches the memory you have, open the model page to see what the model is, then follow the setup guide. Phones use the free PocketPal AI app. Every computer tier turns the model into a local agent with Hermes Agent, the open agent from Nous Research, and most of them run the model with Ollama.

What "uncensored" means here. Every model on this page is a community-modified version of an open model, with its refusal behavior reduced or removed. None is an official release from Google, Qwen, NVIDIA, Z.ai or DeepSeek. The model will not push back on risky requests or risky actions, so in Hermes keep the approval prompts on and read each file write or command before you allow it. What uncensored AI is, and whether it's legal

What we checked. Files, sizes and commands were checked against each publisher's Hugging Face page and the Ollama and Hermes documentation in November 2026. YouRunAI has not run every setup on every machine, and the hardware advice is an estimate unless a guide says otherwise.

SECTION 01 / 10

How the computer setups work

Every Ollama + Hermes guide on this page is the same four steps:

  1. Install Ollama from ollama.com/download.
  2. Set the context to 64k. Open Ollama's Settings and move the Context length slider to 64k. Hermes needs the room, and Ollama otherwise starts at 4,096 tokens on GPUs under 24 GB. (On Linux the guide gives one command instead.)
  3. Download the model with the one ollama pull command in the guide.
  4. Connect Hermes. On Windows and Mac, use the free Hermes Desktop app. Ollama installs it if needed and connects it to the model:
bash
ollama launch hermes-desktop --model <the model from the guide>

To switch models later, run the same command with the other model's name. Prefer the terminal (or on Linux)? Use ollama launch hermes --model <the model from the guide> instead.

Each guide ends with a short task you paste into Hermes, which has it create and review a file, so you can see the agent really works.

Why some tiers use llama.cpp instead. Ollama cannot download a model from Hugging Face when the file is split into several parts. The biggest builds on this page are split, so their guides use llama.cpp's server, and Hermes connects to it in the same way. DeepSeek is too big for any single computer, so it runs on a rented GPU server.

Scroll to compare →
TierModelDownloadRuns with
1 · SmartphoneLFM3-1.7B Uncensored1.13 GBPocketPal AI
2 · Entry-level laptop, 8 GB (GPU or unified memory)Qwen3.5 4B Amadeus2.8 GBOllama + Hermes
3 · Gaming PC, 12–16 GB GPU, or 16 GB MacGemma 4 12B Uncensored6.9 GBOllama + Hermes
4 · 24 GB GPU or 32 GB MacQwen3.8 27B Uncensored v316.6 GBOllama + Hermes
5 · 48–64 GB machineNemotron 3.5 Bolt 74B Uncensored29.1 / 51.7 GBOllama or llama.cpp + Hermes
6 · 128–256 GB workstationQwen3.8 Flash Next Uncensored · GLM-5.3 Flash Abliterated98.5 GB · 109–200 GBllama.cpp + Hermes
7 · GPU cluster / cloudDeepSeek V4.1 Flash 1017 Uncensored~355 GB, in 48 partsSGLang on 4 × H200 + Hermes
SECTION 02 / 10

Tier 1 · Smartphone: LFM3-1.7B Uncensored

Hardware: an iPhone (iOS 15.1 or newer) or an Android phone. Download: 1.13 GB.

AtomicChat's uncensored build of Liquid AI's LFM3-1.7B is small enough to run fully offline on a phone. Install the free PocketPal AI app, add the model from Hugging Face inside the app, load it and chat. Nothing leaves your phone once the file is downloaded.

SECTION 03 / 10

Tier 2 · Entry-level laptop with 8 GB (GPU or unified memory): Qwen3.5 4B Amadeus

Hardware: a laptop with an 8 GB GPU, or a Mac with 8 GB of unified memory. Download: 2.8 GB.

Jitheswar's Amadeus is an abliterated build of Qwen's Qwen3.5-4B: the refusal behavior is removed without any new training. The publisher reports 1 refusal on its 304 test prompts, down from 231 for the original model, and slightly lower scores than the original on truthfulness and instruction-following tests. Those are the publisher's own numbers. It keeps Qwen3.5's thinking mode and image input.

Use the Q4_K_M file, the smallest in the repository. It leaves the most room on an 8 GB machine:

bash
ollama pull hf.co/Jitheswar/Qwen3.5-4B-Amadeus:Q4_K_M ollama launch hermes-desktop --model hf.co/Jitheswar/Qwen3.5-4B-Amadeus:Q4_K_M

On a Mac with 8 GB of unified memory the model shares that memory with macOS, so close other apps. There is also a 3.6 GB Q6_K file with higher quality, for machines with memory to spare. The fit on 8 GB is an estimate, not a YouRunAI measurement.

Follow the four steps in "How the computer setups work" above: install Ollama, set the context to 64k, pull the model, then launch Hermes. If the model runs out of memory with a 64k context, move Ollama's context slider down to 32k. The publisher's page does not report tool-calling tests for this build, and a 4B model can struggle with long multi-step agent tasks, so check what Hermes actually wrote.

SECTION 04 / 10

Tier 3 · Gaming PC with a 12–16 GB GPU, or Mac with 16 GB unified memory: Gemma 4 12B Uncensored

Hardware: a gaming PC with a 12–16 GB GPU, or a Mac with 16 GB of unified memory. Download: 6.9 GB.

HauhauCS's Balanced uncensored build of Google's quantization-aware Gemma 4 12B. HauhauCS reports 0 refusals on its 465 test prompts. That is the publisher's own number.

bash
ollama pull hf.co/HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M
SECTION 05 / 10

Tier 4 · 24 GB GPU or 32 GB Mac: Qwen3.8 27B Uncensored v3

Hardware: one 24 GB GPU (RTX 4090 or 3090) or a 32 GB Apple Silicon Mac. There is also a 10.2 GB build for 12 GB cards. Download: 16.6 GB.

InterpreticAI's uncensored Qwen3.8 27B, built on Nous Research's Arete-27B, with the remaining political censorship removed. This is the strongest model on this page that fits on one consumer GPU.

bash
ollama pull hf.co/InterpreticAI/Qwen3.8-27B-Uncensored-v3-GGUF:Q4_K_M
SECTION 06 / 10

Tier 5 · 48–64 GB machines: Nemotron 3.5 Bolt 74B Uncensored

Hardware: a 64 GB Mac or workstation for the 51.7 GB build, or a 48 GB machine for the 29.1 GB build. Download: 29.1 GB or 51.7 GB.

AtomicChat's uncensored build of NVIDIA's Nemotron 3.5 Bolt, a mixture-of-experts model built for local agents. It uses about 9B of its 74B parameters for each token, so it is fast for its size. AtomicChat reports 20 of 20 valid tool calls after its edit.

SECTION 07 / 10

Tier 6 · 128–256 GB workstations: Qwen3.8 Flash Next and GLM-5.3 Flash

Hardware: a Mac Studio or workstation with 128 GB of memory or more. Download: 98.5 GB (Qwen3.8 Flash Next) or 109–200 GB (GLM-5.3 Flash). Plan for a long download.

Two large mixture-of-experts models. Both guides use llama.cpp, because the GLM builds are split into several files and Ollama's support for Qwen3.8 Flash Next's new architecture with this community file is not documented.

SECTION 08 / 10

Tier 7 · GPU cluster or cloud: DeepSeek V4.1 Flash 1017 Uncensored

Hardware: a rented server with 4 × NVIDIA H200 (564 GB of GPU memory), at least 256 GB of RAM and 700 GB of disk. Your own computer only runs Hermes and an SSH tunnel.

dealignai's uncensored DeepSeek V4.1 Flash runs with SGLang on the rented server. Hermes on your computer connects to it through a private SSH tunnel. Rent by the hour and stop the server when you are done.

SECTION 09 / 10

If something goes wrong

  • Hermes answers in chat but never reads or writes files. Make sure you started Hermes inside the folder the guide creates, and that ollama ps shows the model loaded with a 65,536-token context. Small models (tiers 1–2) fail multi-step agent work more often. Try the next tier up if your hardware allows it.
  • Ollama says the architecture is unknown. Update Ollama to 0.40.16 or newer and run the commands again.
  • Out of memory, or very slow. Choose the smaller build in the guide, or lower the context to 32,768 tokens as the guide explains.
  • Not sure what your machine can run? Save your hardware and YouRunAI rates every model for it.
SECTION 10 / 10

Keep going

KEEP BUILDING

See what your machine can run.

Save your hardware and YouRunAI rates every model and workflow for it.