Gemma-3-12B-IT fine-tuned for uncensored creative writing and roleplay. Made by RACER IS OP.

ollama run R4C3R/gemma-3-12b-it-heretic:q4_k_m

curl http://localhost:11434/api/chat \
  -d '{
    "model": "R4C3R/gemma-3-12b-it-heretic:q4_k_m",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='R4C3R/gemma-3-12b-it-heretic:q4_k_m',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'R4C3R/gemma-3-12b-it-heretic:q4_k_m',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

2 models

Size / Usage

Context

Input

gemma-3-12b-it-heretic:q4_k_m

7.3GB · 128K context window · Text · 1 month ago

gemma-3-12b-it-heretic:q4_k_m

7.3GB

128K

Text

gemma-3-12b-it-heretic:q5_k_m

8.5GB · 128K context window · Text · 1 month ago

gemma-3-12b-it-heretic:q5_k_m

8.5GB

128K

Text

Readme

🏴 Gemma-3-12B-IT-Heretic

Heretic Series by RACER IS OP

Gemma-3-12B-IT-Heretic is a decensored variant of Google’s largest Gemma 3 instruct model. Features 128K context, strong multilingual support, and Google’s latest architecture — without refusal guardrails.

Who this is for — developers who want the full power of Gemma 3 at 12B scale without censorship. Excellent for creative writing, roleplay, and unrestricted chat on 16 GB+ hardware.

Quickstart

ollama run R4C3R/gemma-3-12b-it-heretic

VRAM Guide (choose your quant)

Quant	VRAM	When to use
`q4_k_m`	~7.2 GB	Best balance — fits 10-12 GB GPUs
`q5_k_m`	~8.4 GB	Higher quality, needs 12 GB+
`q8_0`	~12.5 GB	Maximum quality, needs 16 GB+

On a 10-12 GB GPU? q4_k_m works great. Have 16-24 GB? Go q5_k_m or q8_0 for best quality.

Links

Hugging Face · sdad.pro · Heretic

License: Gemma License

Made with love by RACER IS OP — follow for more uncensored models in the Heretic Series.

# 🏴 Gemma-3-12B-IT-Heretic

> **Heretic Series** by RACER IS OP

---

Gemma-3-12B-IT-Heretic is a decensored variant of Google's largest Gemma 3 instruct model. Features 128K context, strong multilingual support, and Google's latest architecture — without refusal guardrails.

**Who this is for** — developers who want the full power of Gemma 3 at 12B scale without censorship. Excellent for creative writing, roleplay, and unrestricted chat on 16 GB+ hardware.

---

### Quickstart

```bash
ollama run R4C3R/gemma-3-12b-it-heretic
```

### VRAM Guide (choose your quant)

| Quant | VRAM | When to use |
|-------|------|-------------|
| `q4_k_m` | ~7.2 GB | Best balance — fits 10-12 GB GPUs |
| `q5_k_m` | ~8.4 GB | Higher quality, needs 12 GB+ |
| `q8_0` | ~12.5 GB | Maximum quality, needs 16 GB+ |

> On a 10-12 GB GPU? `q4_k_m` works great. Have 16-24 GB? Go `q5_k_m` or `q8_0` for best quality.

### Links

[Hugging Face](https://huggingface.co/saidutta69/Gemma-3-12B-IT-heretic) · [sdad.pro](https://sdad.pro) · [Heretic](https://github.com/p-e-w/heretic)

**License:** [Gemma License](https://huggingface.co/google/gemma-3-12b-it/blob/main/LICENSE)

---

*Made with love by RACER IS OP — follow for more uncensored models in the Heretic Series.*

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)