Instructions to use Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ")
model = AutoModelForMultimodalLM.from_pretrained("Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ

SGLang

How to use Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ 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 "Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ" \
    --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": "Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ" \
        --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": "Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ with Docker Model Runner:
```
docker model run hf.co/Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ
```

MiMo-V2.6-Distill-Qwen-9B (W4A16 Quantized Series)

This repository provides production-grade W4A16 quantized checkpoints of XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B, quantized using AutoRound / SignRound.

These checkpoints drastically reduce VRAM overhead while retaining agentic problem solving, coding, tool-calling, and multimodal decision-making capabilities. Non-text modules (visual encoders) and Multi-Token Prediction (MTP) layers are preserved in native bfloat16 to maintain peak reasoning fidelity.

Quantization Details

Method: AutoRound / SignRound (iters=1000, sym=True, group_size=32)
Scheme: W4A16 (4-bit weights, 16-bit activations)
Calibration: 512 samples, sequence length 2048 (batch_size=2, gradient_accumulate_steps=4)
Preserved Modules: mtp, mtp.fc, and visual kept in unquantized bfloat16 for exact multimodal and speculative execution.

Serving with vLLM

Run high-throughput inference with speculative decoding (MTP) and tool-calling enabled:

vllm serve Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ \
  --port 8000 \
  --host 0.0.0.0 \
  --max-model-len 32768 \
  --kv-cache-dtype fp8 \
  --gpu-memory-utilization 0.90 \
  --enable-prefix-caching \
  --enable-chunked-prefill \
  --max-num-batched-tokens 12288 \
  --max-num-seqs 128 \
  --trust-remote-code \
  --dtype bfloat16 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --reasoning-parser qwen3 \
  --default-chat-template-kwargs '{"enable_thinking": false}' \
  --speculative-config '{"method":"mtp","num_speculative_tokens":1}'

Inference Example: Structured Decision Models

When using modern or nightly vLLM releases (> v0.32.0), these checkpoints can be queried directly as structured vision-decision engines:

import base64
import json
import httpx

API_URL = "http://localhost:8000/v1/systemone"
MODEL_ID = "Vishva007/MiMo-V2.6-Distill-Qwen-9B-W4A16-GPTQ"
IMAGE_PATH = "cats.jpg"

def to_data_uri(path: str) -> str:
    with open(path, "rb") as f:
        b64 = base64.b64encode(f.read()).decode("utf-8")
    return f"data:image/jpeg;base64,{b64}"

payload = {
    "model": MODEL_ID,
    "state": "Examine the image and check if it contains a cat.",
    "images": [to_data_uri(IMAGE_PATH)],
    "questions": {
        "is_cat": {
            "type": "choice",
            "instructions": "Determine if a cat is clearly visible in the image.",
            "criteria": {
                "yes": "A cat is present",
                "no": "No cat is visible",
            },
        }
    },
}

response = httpx.post(
    API_URL,
    json=payload,
    headers={"Authorization": "Bearer EMPTY"},
    timeout=60.0,
)

print(json.dumps(response.json(), indent=2, ensure_ascii=False))

🚀 Deploy on RunPod

One-click launch environments pre-configured with PyTorch, CUDA, and dependencies for fine-tuning or quantization.

🎁 Need GPU compute? Sign up via RunPod and get $5–$500 in free credits when you add your first $10.

PyTorch 2.15

Template	CUDA Version	Docker Image	Template ID	Deploy
PyTorch 2.15 (CUDA 13.2)	13.2	`vishva123/cuda-13.2-pytorch-2.15-runpod`	`0rsw686010`
PyTorch 2.15 (CUDA 13.4)	13.4	`vishva123/cuda-13.4-pytorch-2.15-runpod`	`0s0rhdfaqy`

PyTorch 2.14

Template	CUDA Version	Docker Image	Template ID
PyTorch 2.14 (CUDA 12.6)	12.6	`vishva123/cuda-12.6-pytorch-2.14-runpod`	`d7lxsa4w9m`
PyTorch 2.14 (CUDA 13.0)	13.0	`vishva123/cuda-13.0-pytorch-2.14-runpod`	`yk0y6j6rpg`
PyTorch 2.14 (CUDA 13.2)	13.2	`vishva123/cuda-13.2-pytorch-2.14-runpod`	`gsp4gwx0nw`

PyTorch 2.13

Template	CUDA Version	Docker Image	Template ID
PyTorch 2.13 (CUDA 12.6)	12.6	`vishva123/cuda-12.6-pytorch-2.13-runpod`	`gmlupxnxfk`
PyTorch 2.13 (CUDA 13.0)	13.0	`vishva123/cuda-13.0-pytorch-2.13-runpod`	`y3j8xvk4f4`
PyTorch 2.13 (CUDA 13.2)	13.2	`vishva123/cuda-13.2-pytorch-2.13-runpod`	`vigpissn5w`

PyTorch 2.12

Template	CUDA Version	Docker Image	Template ID
PyTorch 2.12 (CUDA 12.6)	12.6	`vishva123/cuda-12.6-pytorch-2.12-runpod`	`ctmz86zmf0`
PyTorch 2.12 (CUDA 13.0)	13.0	`vishva123/cuda-13.0-pytorch-2.12-runpod`	`qjko5yiwzi`
PyTorch 2.12 (CUDA 13.2)	13.2	`vishva123/cuda-13.2-pytorch-2.12-runpod`	`ifg6xmye0f`

Citation & Base Models

@misc{mimo2026v26,
  title={MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement},
  author={{Xiaomi MiMo Team}},
  year={2026},
  howpublished={\url{[https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B)}},
}