Instructions to use drowzeys/MiMo-V2.6-Flash-RL-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drowzeys/MiMo-V2.6-Flash-RL-Abliterated with Transformers:

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

pipe = pipeline("text-generation", model="drowzeys/MiMo-V2.6-Flash-RL-Abliterated", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("drowzeys/MiMo-V2.6-Flash-RL-Abliterated", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use drowzeys/MiMo-V2.6-Flash-RL-Abliterated with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/drowzeys/MiMo-V2.6-Flash-RL-Abliterated

SGLang

How to use drowzeys/MiMo-V2.6-Flash-RL-Abliterated 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 "drowzeys/MiMo-V2.6-Flash-RL-Abliterated" \
    --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": "drowzeys/MiMo-V2.6-Flash-RL-Abliterated",
		"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 "drowzeys/MiMo-V2.6-Flash-RL-Abliterated" \
        --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": "drowzeys/MiMo-V2.6-Flash-RL-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use drowzeys/MiMo-V2.6-Flash-RL-Abliterated with Docker Model Runner:
```
docker model run hf.co/drowzeys/MiMo-V2.6-Flash-RL-Abliterated
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Responsible Use Agreement

This model has had safety refusals removed. That makes it useful for red-teaming, security research, evaluation, and unfiltered assistant tasks — and also removes guardrails a user must therefore supply themselves.

Prohibited uses (you must agree before access is granted):

Anything involving the sexual exploitation or endangerment of minors.
You must be of age 18 years or older to use and download this model.
You agree any information generated that can cause harm in terms of generating recipe, knowledge to make any materials/substances is your own input and responsibility. You will be accountable for any harm/damage caused by your action/input.
Content promoting self-harm or suicide.
Generation of material that is illegal in your jurisdiction, or that targets real individuals for harassment, doxxing, or fraud.
Any use prohibited by the upstream Xiaomi MiMo license.

You are responsible for adding appropriate safety filtering, human review, and access controls for your deployment. The weights are provided as-is, with no warranty. The license is inherited from the upstream Xiaomi MiMo base model — review and comply with it before use or redistribution.

MiMo-V2.6-Flash-RL Abliterated

Drop-in abliterated weights for XiaomiMiMo/MiMo-V2.6-Flash-RL. Same layout as the base checkpoint: FP8 attention, MXFP4 experts, DFlash draft head, and MTP.


Base	`XiaomiMiMo/MiMo-V2.6-Flash-RL`
License	MIT, inherited from the base
Refusal suite	27/32 BYPASS · 5 refuse · 0 garble
Cyber suite	22/22 BYPASS · 0 refuse · 0 garble
Edit	Decoder `self_attn.o_proj` only · λ=3.5
Left stock	Experts, vision, audio, embeddings, DFlash head, MTP

Thinking was off for both suites. A reply counts only when it starts delivering the requested content. This is not a 32/32 checkpoint.

Full credit: XiaomiMiMo/MiMo-V2.6-Flash-RL · tonyd2wild/MiMo-V2.6-Flash-2x-DGX-Spark

Responsible use and gated access

This model has had safety refusals removed. That makes it useful for red-teaming, security research, evaluation, and unfiltered assistant tasks, and it removes guardrails you must supply yourself.

Access is gated. Agreeing to the terms grants access automatically. By requesting access, downloading, or using these weights, you agree to the terms below.

See RESPONSIBLE_USE.md.

Prohibited uses

Anything involving the sexual exploitation or endangerment of minors.
You must be 18 or older to download or use this model.
Information generated that can cause harm, including recipes or knowledge used to make materials or substances, is your own input and your responsibility. You are accountable for harm caused by your actions or inputs.
Content promoting self-harm or suicide.
Material that is illegal in your jurisdiction, or that targets real individuals for harassment, doxxing, or fraud.
Any use prohibited by the upstream Xiaomi MiMo license.

What changed

Only decoder attention output projections (model.layers.*.self_attn.o_proj) differ from the base. λ is 3.5. Experts, the vision encoder, the audio encoder, embeddings, the DFlash draft under dflash/, and model_mtp.safetensors are the base files.

DFlash reads target layers 0, 11, 23, 35, and 47. Layers 0, 11, 23, and 35 were not edited. Layer 47 o_proj has a surgical row edit, so a stock DFlash head can accept fewer draft tokens than it does on the unmodified base. The target model still produces the abliterated continuation.

Serving

On DGX Spark (GB10), keep --gpu-memory-utilization and SGLang --mem-fraction-static at or below 0.85.

The measured suites were collected from an SGLang EAGLE serve, thinking off. The same weights load in the vLLM DFlash recipe at tonyd2wild/MiMo-V2.6-Flash-2x-DGX-Spark. That recipe's dflash/config.json trailing-comma fix still applies. Pass chat_template_kwargs.enable_thinking: false when you want the thinking-off behavior measured above.

Vendor sampling defaults are temperature 1.0 and top_p 0.95.

Downloads last month: -

Safetensors

Model size

311B params

Tensor type

F32

BF16

F8_E4M3

Model tree for drowzeys/MiMo-V2.6-Flash-RL-Abliterated

Base model

XiaomiMiMo/MiMo-V2.6-Flash-RL

Quantized

(28)

this model