Instructions to use ressl/MiniMax-M3-uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ressl/MiniMax-M3-uncensored with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ressl/MiniMax-M3-uncensored", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ressl/MiniMax-M3-uncensored", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("ressl/MiniMax-M3-uncensored", trust_remote_code=True, device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ressl/MiniMax-M3-uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ressl/MiniMax-M3-uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ressl/MiniMax-M3-uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ressl/MiniMax-M3-uncensored

SGLang

How to use ressl/MiniMax-M3-uncensored with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ressl/MiniMax-M3-uncensored" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ressl/MiniMax-M3-uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ressl/MiniMax-M3-uncensored" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ressl/MiniMax-M3-uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ressl/MiniMax-M3-uncensored with Docker Model Runner:
```
docker model run hf.co/ressl/MiniMax-M3-uncensored
```

MiniMax-M3-uncensored / README.md

ressl

Upload README.md with huggingface_hub

f5faea4 verified 25 days ago

preview code

Raw

History Blame Contribute Delete

4.16 kB

	---
	license: other
	base_model: MiniMaxAI/MiniMax-M3
	base_model_relation: finetune
	library_name: transformers
	pipeline_tag: text-generation
	language: [en]
	tags:
	- uncensored
	- abliterated
	- moe
	- minimax
	- security
	---

	![MiniMax-M3-uncensored](banner.png)

	# MiniMax-M3-uncensored (BF16)

	TL;DR: an uncensored build of [MiniMaxAI/MiniMax-M3](https://huggingface.co/MiniMaxAI/MiniMax-M3)
	(428B-parameter MoE, 23B active), with 0 hard refusals on harmful prompts while the model's
	capabilities stay intact. Full-precision BF16, 796 GB.

	> ⚠️ This model is genuinely uncensored, it will comply with requests a stock model refuses.
	>
	> Intended use, the constructive side. An assistant that does not refuse is genuinely useful for
	> ethical hacking, security research, and penetration testing: red-teaming, analyzing malware and
	> exploit code, writing detection/YARA rules, reviewing vulnerabilities, and studying attack
	> techniques without the model bailing out mid-task. Use it lawfully and responsibly, you are
	> accountable for what you do with it.

	## Facts & figures

	\| \| \|
	\|---\|---\|
	\| Base model \| [MiniMaxAI/MiniMax-M3](https://huggingface.co/MiniMaxAI/MiniMax-M3) (428B total / 23B active, MoE, multimodal, 1M context) \|
	\| Precision \| BF16 (796 GB, 59 shards) \|
	\| Effective refusals \| 0/16 hard-refusals on harmful prompts (mlabonne/harmful_behaviors); the base model deliberates or refuses \|
	\| Modified weights \| attention `o_proj` + every residual-writing `down_proj` (dense, shared expert, and all 128 routed experts per MoE layer), all 60 layers \|
	\| Coherence \| intact (multimodal, reasoning and MoE routing preserved) \|

	## Uncensoring, verified

	Generation on harmful prompts, hard-refusal phrases only ("I cannot" / "I won't" etc.):

	\| Prompt set \| Prompts \| Hard refusals \|
	\|---\|---:\|:---:\|
	\| mlabonne/harmful_behaviors \| 16 \| 0/16 (0.0%) \|

	The abliteration is a weight property: it survives quantization, so downstream NVFP4 / GGUF builds
	keep the same behavior.

	> ℹ️ MiniMax-M3 has a reasoning mode (`<mm:think>`). The model thinks before answering; the
	> uncensored build reasons about how to fulfill a request rather than whether to refuse. For direct
	> answers, disable thinking in your client.

	## Run it with transformers

	```python
	from transformers import AutoModelForImageTextToText, AutoTokenizer, AutoConfig
	tok = AutoTokenizer.from_pretrained("ressl/MiniMax-M3-uncensored")
	cfg = AutoConfig.from_pretrained("ressl/MiniMax-M3-uncensored")
	model = AutoModelForImageTextToText.from_pretrained(
	"ressl/MiniMax-M3-uncensored", config=cfg, dtype="bfloat16", device_map="auto")
	```

	## Run it with vLLM

	```bash
	vllm serve ressl/MiniMax-M3-uncensored \
	--tensor-parallel-size 8 --tool-call-parser minimax_m3 --reasoning-parser minimax_m3 --trust-remote-code
	```

	MiniMax-M3 needs a recent vLLM with M3 support (for RTX PRO 6000 / Blackwell see
	[0xSero/minimax-m3-sm120](https://github.com/0xSero/minimax-m3-sm120)). The 428B MoE needs multi-GPU
	at BF16; an NVFP4 quant (NVIDIA ModelOpt, following
	[nvidia/MiniMax-M3-NVFP4](https://huggingface.co/nvidia/MiniMax-M3-NVFP4)) shrinks it to ~230 GB and
	runs on a single Blackwell node.

	## Quality & limitations

	- 0/16 hard refusals on a harmful-prompt sample; not a full capability benchmark.
	- BF16 is large (796 GB); for single-node serving, produce an NVFP4 quant via NVIDIA's ModelOpt
	recipe on this checkpoint (the abliteration is a weight property and survives quantization).
	- The reasoning mode is on by default (see the note above).

	## ❤️ Support

	Producing and validating an uncensored build of a brand-new 428B MoE was a lot of work. If it's
	useful to you, I'd genuinely appreciate your support on [Patreon](https://www.patreon.com/cw/ressl) 🙏,
	more at [ressl.ch](https://ressl.ch/).

	## License & credits

	License inherited from the base model by MiniMaxAI. Uncensoring and validation by
	Robert Ressl ([Hugging Face](https://huggingface.co/ressl) · [Website](https://ressl.ch/) · [LinkedIn](https://www.linkedin.com/in/robertressl/) · [Patreon](https://www.patreon.com/cw/ressl)).