Instructions to use unsloth/MiniMax-M2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/MiniMax-M2 with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/MiniMax-M2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/MiniMax-M2")
model = AutoModelForCausalLM.from_pretrained("unsloth/MiniMax-M2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unsloth/MiniMax-M2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/MiniMax-M2"
# 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-M2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/MiniMax-M2

SGLang

How to use unsloth/MiniMax-M2 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-M2" \
    --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-M2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-M2" \
        --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-M2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use unsloth/MiniMax-M2 with Docker Model Runner:
```
docker model run hf.co/unsloth/MiniMax-M2
```

danielhanchen commited on Nov 1, 2025

Commit

fe33316

verified ·

1 Parent(s): e2fe25a

Update chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +13 -2

chat_template.jinja CHANGED Viewed

@@ -1,3 +1,4 @@
 {# ----------‑‑‑ special token variables ‑‑‑---------- #}
 {%- set toolcall_begin_token   = '<minimax:tool_call>'         -%}
 {%- set toolcall_end_token     = '</minimax:tool_call>'        -%}
@@ -90,8 +91,17 @@
             {%- set reasoning_content = message.reasoning_content %}
         {%- else %}
             {%- if '</think>' in content %}
-                {%- set reasoning_content = content.split('</think>')[0].strip('\n').split('<think>')[-1].strip('\n') %}
-                {%- set content = content.split('</think>')[-1].strip('\n') %}
             {%- endif %}
         {%- endif %}
         {%- if reasoning_content and loop.index0 > ns.last_user_index -%}
@@ -157,3 +167,4 @@
 {%- if add_generation_prompt -%}
 {{- ']~b]ai' ~ '\n' ~ '<think>' ~ '\n' }}
 {%- endif -%}

+{# Unsloth template fixes #}
 {# ----------‑‑‑ special token variables ‑‑‑---------- #}
 {%- set toolcall_begin_token   = '<minimax:tool_call>'         -%}
 {%- set toolcall_end_token     = '</minimax:tool_call>'        -%}
             {%- set reasoning_content = message.reasoning_content %}
         {%- else %}
             {%- if '</think>' in content %}
+                {# Unsloth template fixes - must change to for loop since llama.cpp will error out if not #}
+                {%- set parts = content.split('</think>') %}
+                {%- for part in parts %}
+                    {%- if loop.index0 == 0 -%}
+                        {%- set reasoning_content = part.strip('\n') %}
+                        {%- set reasoning_content = (reasoning_content.split('<think>')|last) %}
+                        {%- set reasoning_content = reasoning_content.strip('\n') -%}
+                    {%- else -%}
+                        {%- set content = part.strip('\n') %}
+                    {%- endif %}
+                {%- endfor %}
             {%- endif %}
         {%- endif %}
         {%- if reasoning_content and loop.index0 > ns.last_user_index -%}
 {%- if add_generation_prompt -%}
 {{- ']~b]ai' ~ '\n' ~ '<think>' ~ '\n' }}
 {%- endif -%}
+{# Copyright 2025-present Unsloth. Apache 2.0 License. #}