Instructions to use a2s-ai/MiniMax-M2-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use a2s-ai/MiniMax-M2-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="a2s-ai/MiniMax-M2-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("a2s-ai/MiniMax-M2-AWQ", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use a2s-ai/MiniMax-M2-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "a2s-ai/MiniMax-M2-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "a2s-ai/MiniMax-M2-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/a2s-ai/MiniMax-M2-AWQ

SGLang

How to use a2s-ai/MiniMax-M2-AWQ 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 "a2s-ai/MiniMax-M2-AWQ" \
    --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": "a2s-ai/MiniMax-M2-AWQ",
		"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 "a2s-ai/MiniMax-M2-AWQ" \
        --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": "a2s-ai/MiniMax-M2-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use a2s-ai/MiniMax-M2-AWQ with Docker Model Runner:
```
docker model run hf.co/a2s-ai/MiniMax-M2-AWQ
```

HuggingFace Container User commited on Nov 5, 2025

Commit

6ef66ae

1 Parent(s): 26ab70b

fork: 05.11.2025

Browse files

Files changed (4) hide show

model-00016-of-00041.safetensors +3 -0
model-00017-of-00041.safetensors +3 -0
model-00018-of-00041.safetensors +3 -0
model-00019-of-00041.safetensors +3 -0

model-00016-of-00041.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c529e29ff7f8fb7b71e1b48a607fb44162de3e52a6fb4978d97c88c1dcc66320
+size 3000144016

model-00017-of-00041.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:aa08176464a10afe3188caf0fa40e95377be3c1391dc0dad148e8570f5d06775
+size 2999227968

model-00018-of-00041.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0c484c513b19332876b8a9c60d9c048d35bd7f901dee85626b0e4df3026b2b3b
+size 3000142744

model-00019-of-00041.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5547279b84b99df76481050b1fa52a620746c6eb37ef7a57fd19a8234ef31588
+size 2999228296