Instructions to use QuantTrio/MiniMax-M2.1-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantTrio/MiniMax-M2.1-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="QuantTrio/MiniMax-M2.1-AWQ", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuantTrio/MiniMax-M2.1-AWQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("QuantTrio/MiniMax-M2.1-AWQ", trust_remote_code=True)
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

vLLM

How to use QuantTrio/MiniMax-M2.1-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantTrio/MiniMax-M2.1-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": "QuantTrio/MiniMax-M2.1-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantTrio/MiniMax-M2.1-AWQ

SGLang

How to use QuantTrio/MiniMax-M2.1-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 "QuantTrio/MiniMax-M2.1-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": "QuantTrio/MiniMax-M2.1-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 "QuantTrio/MiniMax-M2.1-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": "QuantTrio/MiniMax-M2.1-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QuantTrio/MiniMax-M2.1-AWQ with Docker Model Runner:
```
docker model run hf.co/QuantTrio/MiniMax-M2.1-AWQ
```

Thank you for your Quant!

by mtcl - opened Dec 29, 2025

Discussion

mtcl

Dec 29, 2025

DOwnloading it as we speak. I will report back. Thank you :)

i have noticed that while running your qunats i do not see mistral error message while starting up the server which i see in the cyanwiki's quants. My OCD prefers your quants lol

mtcl

Dec 29, 2025

Amazing quant! Runs perfectly on 2x6000 pros! Life is good.

CihanDogan

Dec 29, 2025

Thanks for the quant - any chance you could do a 5bit one as well? Thank you

JunHowie

QuantTrio org Dec 30, 2025

Thanks for the quant - any chance you could do a 5bit one as well? Thank you

Maybe what you meant was GPTQ mixed? We don’t have plans for that at the moment.

eugreugr

Dec 30, 2025

DOwnloading it as we speak. I will report back. Thank you :)

i have noticed that while running your qunats i do not see mistral error message while starting up the server which i see in the cyanwiki's quants. My OCD prefers your quants lol

For some reason, cyankiwi quant is faster for me - I get 40 t/s with that one, and 27 t/s with QuantTrio on dual DGX Spark cluster....

CihanDogan

Dec 30, 2025

I'll run some benchmarks comparing the quants later today

paolovic

Dec 30, 2025

please, let us know @CihanDogan

mtcl

Dec 30, 2025

DOwnloading it as we speak. I will report back. Thank you :)

i have noticed that while running your qunats i do not see mistral error message while starting up the server which i see in the cyanwiki's quants. My OCD prefers your quants lol

For some reason, cyankiwi quant is faster for me - I get 40 t/s with that one, and 27 t/s with QuantTrio on dual DGX Spark cluster....

it is opposite for me on 2X6000 Pros.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment