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

Libraries

How to use MiniMaxAI/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="MiniMaxAI/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("MiniMaxAI/MiniMax-M3.1-Flash", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("MiniMaxAI/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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MiniMaxAI/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 "MiniMaxAI/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": "MiniMaxAI/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/MiniMaxAI/MiniMax-M3.1-Flash

SGLang

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

Improve factual reliability and Jinja2 compatibility in chat template

#15

by yasu-oh - opened 3 days ago

base: refs/heads/main

←

from: refs/pr/15

Discussion Files changed

-1

Files changed (1) hide show

chat_template.jinja +3 -1

chat_template.jinja CHANGED Viewed

@@ -36,7 +36,7 @@
 {#- Tool Rendering Functions ============================================== -#}
 {%- macro render_tool_namespace(namespace_name, tool_list) -%}
 {%- for tool in tool_list -%}
-<tool>{{ tool.function | tojson(ensure_ascii=False) }}</tool>
 {% endfor -%}
 {%- endmacro -%}
 {%- macro visible_text(content) -%}
@@ -76,6 +76,8 @@
         {{- 'Your model version is MiniMax-M3.1, developed by MiniMax. Knowledge cutoff: January 2026. Founded in early 2022, MiniMax is a global AI foundation model company committed to advancing the frontiers of AI towards AGI.' }}
     {%- endif -%}
     {#- Thinking mode instructions -#}
     {{- '\n\n<thinking_instructions>\n' }}
     {{- 'You have a thinking capability that allows you to reason step by step before responding. When thinking is enabled, wrap your reasoning in ' ~ think_begin_token ~ think_end_token ~ ' tags before your response. When thinking is disabled, begin your response directly after the ' ~ think_end_token ~ ' prefix. When thinking is adaptive, decide on your own whether to think for the current turn.\n' }}

 {#- Tool Rendering Functions ============================================== -#}
 {%- macro render_tool_namespace(namespace_name, tool_list) -%}
 {%- for tool in tool_list -%}
+<tool>{{ tool.function | tojson }}</tool>
 {% endfor -%}
 {%- endmacro -%}
 {%- macro visible_text(content) -%}
         {{- 'Your model version is MiniMax-M3.1, developed by MiniMax. Knowledge cutoff: January 2026. Founded in early 2022, MiniMax is a global AI foundation model company committed to advancing the frontiers of AI towards AGI.' }}
     {%- endif -%}
+    {#- Factual reliability guidance: conservative, task-agnostic, and not benchmark-specific. -#}
+    {{- '\n\nWhen answering factual questions, first use facts you actually know or conclusions you can reliably derive. Do not fill gaps with plausible-sounding guesses. For exact details such as names, dates, numbers, software versions, quotations, or citations, answer only when reasonably confident of the specific detail. If you cannot determine an answer reliably from the information available, explicitly say you do not know rather than inventing an answer. Do not claim to have checked a source you did not check. Do not abstain from questions you can solve by sound reasoning or calculation. Follow the user\'s requested answer format.' }}
     {#- Thinking mode instructions -#}
     {{- '\n\n<thinking_instructions>\n' }}
     {{- 'You have a thinking capability that allows you to reason step by step before responding. When thinking is enabled, wrap your reasoning in ' ~ think_begin_token ~ think_end_token ~ ' tags before your response. When thinking is disabled, begin your response directly after the ' ~ think_end_token ~ ' prefix. When thinking is adaptive, decide on your own whether to think for the current turn.\n' }}