Instructions to use unsloth/MiniMax-M3.1-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/MiniMax-M3.1-Flash with Transformers:

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

pipe = pipeline("image-text-to-text", model="unsloth/MiniMax-M3.1-Flash", 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)

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

processor = AutoProcessor.from_pretrained("unsloth/MiniMax-M3.1-Flash", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("unsloth/MiniMax-M3.1-Flash", trust_remote_code=True, 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 unsloth/MiniMax-M3.1-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/MiniMax-M3.1-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/MiniMax-M3.1-Flash",
		"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/unsloth/MiniMax-M3.1-Flash

SGLang

How to use unsloth/MiniMax-M3.1-Flash 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 "unsloth/MiniMax-M3.1-Flash" \
    --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": "unsloth/MiniMax-M3.1-Flash",
		"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 "unsloth/MiniMax-M3.1-Flash" \
        --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": "unsloth/MiniMax-M3.1-Flash",
		"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 unsloth/MiniMax-M3.1-Flash with Docker Model Runner:
```
docker model run hf.co/unsloth/MiniMax-M3.1-Flash
```

danielhanchen commited on about 9 hours ago

Commit

697ee60

verified ·

1 Parent(s): ef16900

Add files using upload-large-folder tool

Browse files

Files changed (22) hide show

model-00001-of-00048.safetensors +3 -0
model-00004-of-00048.safetensors +3 -0
model-00005-of-00048.safetensors +3 -0
model-00006-of-00048.safetensors +3 -0
model-00007-of-00048.safetensors +3 -0
model-00008-of-00048.safetensors +3 -0
model-00009-of-00048.safetensors +3 -0
model-00010-of-00048.safetensors +3 -0
model-00011-of-00048.safetensors +3 -0
model-00012-of-00048.safetensors +3 -0
model-00013-of-00048.safetensors +3 -0
model-00020-of-00048.safetensors +3 -0
model-00025-of-00048.safetensors +3 -0
model-00027-of-00048.safetensors +3 -0
model-00031-of-00048.safetensors +3 -0
model-00032-of-00048.safetensors +3 -0
model-00033-of-00048.safetensors +3 -0
model-00038-of-00048.safetensors +3 -0
model-00039-of-00048.safetensors +3 -0
model-00044-of-00048.safetensors +3 -0
model-00047-of-00048.safetensors +3 -0
model-00048-of-00048.safetensors +3 -0

+version https://git-lfs.github.com/spec/v1
+oid sha256:8b7c561664839e3b2d800c1cd7afe1beb529efa70ce0c2da82d7bb912bf2249b
+size 10213649632

+version https://git-lfs.github.com/spec/v1
+oid sha256:ad32f2c455aa2ab8de4b576ee508cc63ede81490330a5cb251bef533d3fb8299
+size 8506022152

+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b0c83a62826c3427d94b1914805193ea6eb044797946db1569a9ef13b64356
+size 8506023712

+version https://git-lfs.github.com/spec/v1
+oid sha256:aa146faf2cd153211379d8a933df3abea68db75285d1c8f26e6f6ff02ae5f512
+size 4721760520

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef5a921908c37d450e6ca406d6a2fcfc22612f73a4eddba3910dbef1ebcc8c3
+size 4253009184

+version https://git-lfs.github.com/spec/v1
+oid sha256:6c53f014619e633c013b71d4599478b06c2a0ea0bd83931eece0ecdcf65f8f00
+size 5518475304

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

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

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

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