Instructions to use EmbeddedLLM/MiniMax-M3-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EmbeddedLLM/MiniMax-M3-FP8-dynamic with Transformers:

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

pipe = pipeline("image-text-to-text", model="EmbeddedLLM/MiniMax-M3-FP8-dynamic", 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("EmbeddedLLM/MiniMax-M3-FP8-dynamic", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("EmbeddedLLM/MiniMax-M3-FP8-dynamic", 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?"}
        ]
    },
]
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 EmbeddedLLM/MiniMax-M3-FP8-dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EmbeddedLLM/MiniMax-M3-FP8-dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmbeddedLLM/MiniMax-M3-FP8-dynamic",
		"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/EmbeddedLLM/MiniMax-M3-FP8-dynamic

SGLang

How to use EmbeddedLLM/MiniMax-M3-FP8-dynamic 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 "EmbeddedLLM/MiniMax-M3-FP8-dynamic" \
    --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": "EmbeddedLLM/MiniMax-M3-FP8-dynamic",
		"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 "EmbeddedLLM/MiniMax-M3-FP8-dynamic" \
        --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": "EmbeddedLLM/MiniMax-M3-FP8-dynamic",
		"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 EmbeddedLLM/MiniMax-M3-FP8-dynamic with Docker Model Runner:
```
docker model run hf.co/EmbeddedLLM/MiniMax-M3-FP8-dynamic
```

MiniMax-M3-FP8-dynamic / README.md

pstan

Add files using upload-large-folder tool

cf38c3b verified about 10 hours ago

preview code

Raw

History Blame Contribute Delete

2.23 kB

	---
	license: other
	base_model: MiniMaxAI/MiniMax-M3
	pipeline_tag: image-text-to-text
	library_name: transformers
	tags:
	- minimax-m3
	- fp8
	- compressed-tensors
	- llm-compressor
	- vllm
	- rocm
	- conversational
	- image-text-to-text
	---

	# MiniMax-M3-FP8-dynamic

	## Model Overview

	This model is an FP8 dynamic quantized version of [MiniMaxAI/MiniMax-M3](https://huggingface.co/MiniMaxAI/MiniMax-M3).

	- Base model: `MiniMaxAI/MiniMax-M3`
	- Optimization: FP8 dynamic quantization
	- Format: safetensors / compressed-tensors
	- Validated runtime: vLLM OpenAI-compatible server
	- Tested hardware: AMD MI350, tensor parallel size 8

	MiniMax-M3 is a native multimodal MoE model. The original model card describes it as a ~428B parameter model with ~23B activated parameters and 1M context support.

	## License

	This quantized checkpoint follows the license terms of the base model, [MiniMaxAI/MiniMax-M3](https://huggingface.co/MiniMaxAI/MiniMax-M3). The Hugging Face model-card metadata uses `license: other` because the MiniMax community license is not one of the Hub's enumerated license identifiers.

	## Model Optimizations

	This checkpoint uses FP8 dynamic quantization to reduce memory and disk requirements while preserving model quality. Validation below compares this quantized checkpoint against the BF16 `MiniMaxAI/MiniMax-M3` baseline.

	## Evaluation

	The model was evaluated against BF16 `MiniMaxAI/MiniMax-M3`. Scores are averaged across seeds.

	\| Benchmark \| MiniMaxAI/MiniMax-M3 \| EmbeddedLLM/MiniMax-M3-FP8-dynamic \| Recovery (%) \|
	\|---\|---:\|---:\|---:\|
	\| GSM8k Platinum \| 95.81 \| 95.92 \| 100.12 \|
	\| IfEval \| 80.65 \| 79.42 \| 98.47 \|
	\| AIME 2025 \| 20.83 \| 19.17 \| 92.00 \|
	\| GPQA diamond \| 77.78 \| 77.95 \| 100.22 \|
	\| Math 500 \| 81.20 \| 79.93 \| 98.44 \|
	\| Lcb Codegeneration V6 \| 37.14 \| 35.62 \| 95.90 \|
	\| MMLU Pro Chat \| 79.85 \| 79.62 \| 99.72 \|

	## Evaluation Setup

	- Standard seeds: `42, 1234, 4158`
	- AIME 2025 seeds: `42, 1234, 4158, 5322, 1356, 9843, 3344, 5678`
	- GSM8K Platinum cap: `max_gen_toks=64000`
	- IFEval, AIME, GPQA, Math 500, MMLU Pro Chat cap: `max_gen_toks=4096`
	- LiveCodeBench v6 cap: `max_gen_toks=2048`
	- MiniMax thinking mode: disabled
	- Runners: lm-eval harness and lighteval through LiteLLM endpoint mode