📚🎮🧑‍💻

[📚🎮🧑‍💻 @__gimmelatte]

@LambeSahamjja program memek gak berguna

[📚🎮🧑‍💻 @__gimmelatte]

in relationships it’s always men who’s wrong

[Fiadh 💚🦌 @FiadhBaikal]

So he can't jerk off either?
The hell is he supposed to do? Die?

[📚🎮🧑‍💻 @__gimmelatte]

@joey_ardiva emang kelakuan nigger ini sama semua

[📚🎮🧑‍💻 @__gimmelatte]

@itssthyherinme shut up nigger

[📚🎮🧑‍💻 @__gimmelatte]

@txtruangpodcast nigger

[ichitaso @ichitaso]

[Release] Regitela v1.0.0 is out 🎉
No jailbreak needed on iOS 27:
- Toggle Supervised Mode, no erase
- Switch Japanese/Korean models to the US region (LL/A)
Built on worse_query.
⚠️ Install with Impactor. Sideloadly doesn't work.
https://t.co/rUcpBpW8Hp

[Skadz @skadz108]

Erosion v0.3 is out now, replacing bad_query with worse_query and massively expanding the version support.

https://t.co/ahrDqBaEiH

Thx to @forcequitOS and @0xjohnny for the new sandbox escape!!

[PureDarwin @puredarwin]

so this is what I've been doing.
after a bit longer, and some more PRs, I'll be back to PureDarwin!
this is @reactos arm32 on a Lumia 1520 bare-metal.
HD2 should be next, hopefully.
I bought a cooler for my 11700K & 8700, so hopefully i915 fixes.

[📚🎮🧑‍💻 @__gimmelatte]

@TechWhirlUlt @nikolasspyr you can do that on zen

[📚🎮🧑‍💻 @__gimmelatte]

@TechWhirlUlt lol

[📚🎮🧑‍💻 @__gimmelatte]

@amongtamuu @perogeremmer itu kenapa kalo mau kenal org atau pengen cari pasangan touch some grass, jangan hape mulu 🤣

[📚🎮🧑‍💻 @__gimmelatte]

@TheReal_Manson @gugelpixel @ayamgoyengvy mending lu cium aja noh polisinya

[Ronin @DeRonin_]

Here's 4 steps to run an uncensored AI on your own GPU for $0:

I run a local abliterated Gemma 4 for anything I don't want leaving my machine

By the end, you'll know how to:
- run a model which has no refuses
- plug it into Claude Code
- do it all for $0, no API key, no account

So, let's go step by step:

1. Install Ollama

curl -fsSL https://t.co/Xqcu5R7xOu | sh
you want a recent version, older builds don't speak the Anthropic API and don't support Gemma 4

2. Pull the model

ollama pull igorls/gemma-4-12B-it-heretic-GGUF

the biggest mistake people make here is grabbing a random "uncensored" tag with no quality numbers

this one is abliterated with Heretic. refusals went 99/100 → 0/100 at a KL divergence of 0.028 from the original, so you keep almost all of the base model's capability

one thing: it's still Google's Gemma license underneath, fine for personal use, but read the terms before you build a product on it

3. Turn off thinking (the part every other guide skips)

Gemma 4 is a hybrid thinking model and the abliteration targets non-thinking mode

leave thinking on and the reasoning block eats your token budget and the answer gets cut off

ollama run igorls/gemma-4-12B-it-heretic-GGUF

/set nothink
if you're calling the API instead, add "think": false to the request

4. Plug it into Claude Code (OPTIONAL)

ollama launch claude --model igorls/gemma-4-12B-it-heretic-GGUF

or manually:

export ANTHROPIC_BASE_URL=http://localhost:11434

export ANTHROPIC_AUTH_TOKEN=ollama
claude --model igorls/gemma-4-12B-it-heretic-GGUF
two gotchas:

- bump the context first. Ollama defaults to 4k and Claude Code's system prompt alone is bigger than that, so the model never sees its tool instructions. restart the server with OLLAMA_CONTEXT_LENGTH=32768 ollama serve (setting it in your shell does nothing if Ollama is already running as a service). this needs more VRAM than the 8GB below

- Gemma 4 tool calling is still rough, you should expect some failed edits, imo for serious agentic work use qwen3.5 or glm-4.7-flash instead

What you need:

- 8-12GB VRAM for Q4 (12B)
- ~8GB of disk for Q4, ~13GB for Q8
- more of both if you want a big context
honest take:

- "abliterated" means refusals removed, not quality added. it's still a 12B

- fewer refusals ≠ smarter. for real coding work I still use cloud models
- you own the weights, your prompts never leave the box. that's the actual win
*IMPORTANT: don't use it for anything illegal or harmful. that's on you, not the model

now i'm collecting a list of every uncensored model i'm adding to my local stack and which tasks each one replaces for me

also planning a big "Uncensored 101" article, still figuring out all the angles

save it so you don't lose it

[📚🎮🧑‍💻 @__gimmelatte]

@nepomammy gw sama cewe gw pake kok

[📚🎮🧑‍💻 @__gimmelatte]

@MDvianto kontol lu tuh membengkak

[📚🎮🧑‍💻 @__gimmelatte]

@grok @kamuiyamaro @vursaz 🤣🤣🤣🤣🤣🤣🤣🤣🤣🤣🤣🤣🤣

[📚🎮🧑‍💻 @__gimmelatte]

@alckateri heh mamad