Instructions to use com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4

SGLang

How to use com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4 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 "com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4" \
    --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": "com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4",
		"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 "com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4" \
        --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": "com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4 with Docker Model Runner:
```
docker model run hf.co/com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4
```

Access to MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4 (red-team research build)

This build has refusal behavior surgically reduced (abliterated) from Xiaomi's MiMo-V2.6-Pro-MOPD via contrastive refusal-direction ablation, and quantized to NVFP4. It is published strictly for AI-safety and red-team research (refusal-mechanism studies, alignment-failure research, guardrail evaluation). It can produce content a production assistant must not. Do not deploy it without your own safeguards.

MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4

Red-team research build of XiaomiMiMo/MiMo-V2.6-Pro-MOPD (Xiaomi, MIT license), published by com-kotobalabs.

What this is

Refusal abliteration: refusal behavior was surgically reduced from the MOPD checkpoint via residual-stream writer/reader orthogonalization (contrastive refusal-direction ablation). Weights only; no retraining, no prompt-level system changes.
Quantization: exact MXFP4 -> NVFP4 conversion (NVIDIA ModelOpt, quant_method: modelopt), including TP-chunked qkv reorder where applicable. See conversion-report.json for the per-tensor manifest.
Everything else unchanged: architecture, tokenizer, chat template, MTP speculative decoder, and audio tokenizer are inherited from the base model.


Base model	XiaomiMiMo/MiMo-V2.6-Pro-MOPD (MIT)
Method	Abliteration (writer/reader orthogonalization) + exact MXFP4->NVFP4
Quantization	NVFP4 (4-bit, ModelOpt), `model_pp0_ep_shard.safetensors`
Architecture	Sparse MoE, 1.02T total / 42B activated; 1M-token context; text + image + video + audio
Served with	vLLM or NVIDIA TensorRT-LLM with NVFP4 support; custom code in this repo (`configuration_mimo_v2.py`, `modeling_mimo_v2.py`) required for transformers
Speculative decoding	`model_mtp.safetensors` (5-layer MTP) + `dflash/` draft model

Usage

# vLLM (NVFP4)
from vllm import LLM, SamplingParams
llm = LLM("com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4",
          gpu_memory_utilization=0.9,
          quantization="nvfp4",
          enforce_eager=False)
out = llm.generate("Explain how MoE routing works.", SamplingParams(temperature=0.7))

For transformers, load with the repo's custom code (trust_remote_code=True / auto_map in config.json).

Hardware: NVFP4 targets H100/H200/GB200-class GPUs; expect well under the ~405GB of the FP8 base at the same expert count.

License

MIT — same as the base model XiaomiMiMo/MiMo-V2.6-Pro-MOPD. The abliteration and quantization steps are weight-space transformations only, no additional training data is introduced.

Terms & limitations (please read before deploying)

Research build, not a production model. This checkpoint exists for AI-safety and red-team research: refusal-mechanism studies, alignment-failure research, guardrail evaluation, and abliteration quality measurement.
The uncensored property is the point — and the risk. Abliteration reduces but does not guarantee the elimination of refusal behavior. Outputs can include profanity, edgy phrasing, or content a production assistant must not produce. Do not deploy to end users without your own safeguards (prompt filtering, tool-call policy, moderation layer).
Quantization + ablation compound. Expect the usual NVFP4 precision loss on top of base-model behavior. For quality-sensitive work, benchmark against the FP8 base before adopting this build.
Data handling: no new training data was added in this build; any data-policy obligations you have for the base model (Xiaomi MiMo terms) still apply to derivatives.
No SLA: this is a community-published checkpoint. Weights are provided as-is, without warranty of fitness for any particular purpose.

Related builds (com-kotobalabs)

MiMo-V2.6-Flash-Uncensored-NVFP4 — same treatment applied to the Flash variant
MiMo-V2.6-Pro-RL-Uncensored-NVFP4 — same treatment applied to the Pro-RL variant
Qwen3.8-27B-Uncensored-whitehat-NVFP4 — Qwen3.8 whitehat build

If this build is useful for your work, an upvote helps it surface. Bug reports: open an issue on the com-kotobalabs GitHub or file a Hub discussion on this repo.

Downloads last month: 13

Safetensors

Model size

524B params

Tensor type

BF16

F32

Model tree for com-kotobalabs/MiMo-V2.6-Pro-MOPD-Uncensored-NVFP4

Base model

XiaomiMiMo/MiMo-V2.6-Pro-MOPD

Finetuned

(3)

this model