Instructions to use sparkarena/Minimax-M3-v0-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sparkarena/Minimax-M3-v0-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="sparkarena/Minimax-M3-v0-NVFP4", 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("sparkarena/Minimax-M3-v0-NVFP4", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("sparkarena/Minimax-M3-v0-NVFP4", 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 sparkarena/Minimax-M3-v0-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sparkarena/Minimax-M3-v0-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": "sparkarena/Minimax-M3-v0-NVFP4",
		"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/sparkarena/Minimax-M3-v0-NVFP4

SGLang

How to use sparkarena/Minimax-M3-v0-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 "sparkarena/Minimax-M3-v0-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": "sparkarena/Minimax-M3-v0-NVFP4",
		"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 "sparkarena/Minimax-M3-v0-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": "sparkarena/Minimax-M3-v0-NVFP4",
		"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 sparkarena/Minimax-M3-v0-NVFP4 with Docker Model Runner:
```
docker model run hf.co/sparkarena/Minimax-M3-v0-NVFP4
```

dbotwinick commited on about 1 month ago

Commit

c11e3e4

verified ·

1 Parent(s): 4748da5

Add files using upload-large-folder tool

Browse files

Files changed (18) hide show

.gitattributes +1 -0
model-00002-of-00046.safetensors +3 -0
model-00009-of-00046.safetensors +3 -0
model-00013-of-00046.safetensors +3 -0
model-00014-of-00046.safetensors +3 -0
model-00015-of-00046.safetensors +3 -0
model-00018-of-00046.safetensors +3 -0
model-00020-of-00046.safetensors +3 -0
model-00026-of-00046.safetensors +3 -0
model-00028-of-00046.safetensors +3 -0
model-00031-of-00046.safetensors +3 -0
model-00036-of-00046.safetensors +3 -0
model-00037-of-00046.safetensors +3 -0
model-00039-of-00046.safetensors +3 -0
model-00040-of-00046.safetensors +3 -0
model-00046-of-00046.safetensors +3 -0
model-input-scales-calib.safetensors +3 -0
model.safetensors.index.json.orig +3 -0

@@ -8,3 +8,4 @@
 *.jinja text
 *.txt text
 *.md text

 *.jinja text
 *.txt text
 *.md text
+model.safetensors.index.json.orig filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:1155cadd470721dbe4d3f1cc93e8e537cc1e5206cfcd1fb9c08036e9ac31a452
+size 5364589512

+version https://git-lfs.github.com/spec/v1
+oid sha256:309f64777d63238badf90ccca70aa62e39379469caad9a3e459f014975ac53ba
+size 5360459328

+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0b420c3168cf53601d4e225bca06a2351051cd6174e44121158479cf046932
+size 5366810008

+version https://git-lfs.github.com/spec/v1
+oid sha256:635531cad4c733b07c0cd15493bf646ead437d838bd60c7c008d7928b1e526d4
+size 5360459616

+version https://git-lfs.github.com/spec/v1
+oid sha256:64acb97d83ad74bb30732a16fb5596206733f3df266b6b8289dd25f75f373bcf
+size 5365480504

+version https://git-lfs.github.com/spec/v1
+oid sha256:fd66564b180a10b0ff7ce00a20eb1821b3d491d65edbb97571bdcbaa4d1f7a6a
+size 5366806832

+version https://git-lfs.github.com/spec/v1
+oid sha256:edfaaf5cf4e9000f204e8ca1cebd2100b21b6b2dc228ae3bcc2ccdffbc85da71
+size 5367987760

+version https://git-lfs.github.com/spec/v1
+oid sha256:82d2da38e486372b39ed2c2c0f85a7ece196194b999e23cba525add27ede68a1
+size 5366810512

+version https://git-lfs.github.com/spec/v1
+oid sha256:988a574d0a020777199429a1932654fbcfabf9665f9f638e8de667ef7fde941f
+size 5365481616

+version https://git-lfs.github.com/spec/v1
+oid sha256:dff34373cc418df182c4ce76a0f2129673f9cd0a20ed7251b42f29e98ffb05a2
+size 5365480984

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8502526a18137f3d75eb6e6cbc004874b2bfd7e30e57fe500dc7416bc8fdd266
+size 5366809304

+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c5e227f0a41d2b37f040195b50308ec8199c53134e16c0575c9f8f0c381259
+size 5368570024

+version https://git-lfs.github.com/spec/v1
+oid sha256:2d65fe1469767383b656cf7c3cc124be41494c9c807b013b09c6beb309e9609b
+size 5366811304

+version https://git-lfs.github.com/spec/v1
+oid sha256:e3df51f3c03c0d5132ac9aae4462495f7e199fb07de5cc44427f0654a16f300b
+size 3760924824

+version https://git-lfs.github.com/spec/v1
+oid sha256:b0f82a7282bca4029d16a77636b932f22cffaba0925b7719d59b18209fd99859
+size 3041496

+version https://git-lfs.github.com/spec/v1
+oid sha256:af0caf8ec59bff89a072d28c9f9ddabe915f9ecbf46f88d786fbb93e50cccadb
+size 10565496