Instructions to use Sebesky/MiniMax-M3-W4A16-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sebesky/MiniMax-M3-W4A16-GPTQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="Sebesky/MiniMax-M3-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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Sebesky/MiniMax-M3-W4A16-GPTQ")
model = AutoModelForMultimodalLM.from_pretrained("Sebesky/MiniMax-M3-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?"}
        ]
    },
]
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 Sebesky/MiniMax-M3-W4A16-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sebesky/MiniMax-M3-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": "Sebesky/MiniMax-M3-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/Sebesky/MiniMax-M3-W4A16-GPTQ

SGLang

How to use Sebesky/MiniMax-M3-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 "Sebesky/MiniMax-M3-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": "Sebesky/MiniMax-M3-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 "Sebesky/MiniMax-M3-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": "Sebesky/MiniMax-M3-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 Sebesky/MiniMax-M3-W4A16-GPTQ with Docker Model Runner:
```
docker model run hf.co/Sebesky/MiniMax-M3-W4A16-GPTQ
```

MiniMax-M3-W4A16-GPTQ / README.md

Sebesky

Add files using upload-large-folder tool

21d8eda verified 14 days ago

preview code

Raw

History Blame Contribute Delete

2.29 kB

	---
	base_model: MiniMaxAI/MiniMax-M3
	license: other
	license_name: minimax-community
	license_link: LICENSE
	pipeline_tag: image-text-to-text
	library_name: transformers
	tags:
	- minimax
	- mixture-of-experts
	- moe
	- w4a16
	- int4
	- gptq
	- compressed-tensors
	- quantized
	- vllm
	---

	# MiniMax-M3 — W4A16 (GPTQ)

	4-bit weight quantization of MiniMax-M3 produced with GPTQ via
	[llm-compressor](https://github.com/vllm-project/llm-compressor), stored in the
	compressed-tensors `pack-quantized` format for serving with vLLM / SGLang. Routed-expert
	weights keep the base `w1/w2/w3` naming, so the checkpoint loads against the native M3
	architecture.

	## Quantization

	\| \| \|
	\|---\|---\|
	\| Scheme \| W4A16 (4-bit weights, 16-bit activations) \|
	\| Weights \| int4, symmetric, group size 128 \|
	\| Embeddings \| int4, group size 64 \|
	\| `lm_head` \| bf16 (kept full precision) \|
	\| Left in bf16 \| router gates, lightning-indexer projections, RMSNorms, vision tower \|
	\| KV cache \| bf16 \|
	\| Method \| GPTQ — Hessian error minimization with cross-layer error propagation \|
	\| Format \| compressed-tensors (`pack-quantized`) \|

	All 60 decoder layers are quantized (3 dense + 57 sparse/MoE, 128 experts each).

	## Calibration

	Calibrated on deployment-realistic agentic trajectories — 427 multi-turn tool-use
	rollouts (~8M tokens) rendered through the M3 chat template at up to 32k sequence length,
	padded with a small amount of general-instruction data. The goal is to match the model's real
	serving distribution (multi-turn, tool-calling) rather than generic web text.

	## Quality

	Mean weight-reconstruction error vs the bf16 base is ≈0.125 relative (cosine ≈ 0.993) —
	the expected magnitude for int4 group-128 quantization. This is a weight-space measure;
	evaluate downstream quality on your own target benchmark.

	## Usage

	```bash
	# requires a vLLM build with MiniMax-M3 support
	vllm serve Sebesky/MiniMax-M3-W4A16-GPTQ
	```

	```python
	from transformers import AutoModelForImageTextToText, AutoTokenizer
	model = AutoModelForImageTextToText.from_pretrained("Sebesky/MiniMax-M3-W4A16-GPTQ", device_map="auto")
	tok = AutoTokenizer.from_pretrained("Sebesky/MiniMax-M3-W4A16-GPTQ")
	```

	## License

	Inherits the [MiniMax Community License](LICENSE) from the base model (non-commercial use).