Instructions to use olka-fi/MiniMax-M2.7-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use olka-fi/MiniMax-M2.7-MXFP4 with Transformers:

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

pipe = pipeline("text-generation", model="olka-fi/MiniMax-M2.7-MXFP4", 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("olka-fi/MiniMax-M2.7-MXFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("olka-fi/MiniMax-M2.7-MXFP4", 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 olka-fi/MiniMax-M2.7-MXFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "olka-fi/MiniMax-M2.7-MXFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "olka-fi/MiniMax-M2.7-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/olka-fi/MiniMax-M2.7-MXFP4

SGLang

How to use olka-fi/MiniMax-M2.7-MXFP4 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 "olka-fi/MiniMax-M2.7-MXFP4" \
    --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": "olka-fi/MiniMax-M2.7-MXFP4",
		"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 "olka-fi/MiniMax-M2.7-MXFP4" \
        --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": "olka-fi/MiniMax-M2.7-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use olka-fi/MiniMax-M2.7-MXFP4 with Docker Model Runner:
```
docker model run hf.co/olka-fi/MiniMax-M2.7-MXFP4
```

Has anyone successfully run it on two GB10 machines?

by win10 - opened about 1 month ago

Discussion

win10

about 1 month ago

Has anyone successfully run it on two GB10 machines?

olka-fi

Owner about 1 month ago

Hi, that’s exactly my setup to run it

Any particular questions?

There’s a bug in vLLM about expert parallelism with TP>1 - so just drop this flag and it should be fine

win10

about 1 month ago

I think the output speed is very fast, what do you think?

Hi, that’s exactly my setup to run it

Any particular questions?

There’s a bug in vLLM about expert parallelism with TP>1 - so just drop this flag and it should be fine

olka-fi

Owner about 1 month ago

Yes absolutely!
I was very surprised by the speed.

It is very usable in terms of quality and performance and ATM my daily workhorse.

Need to try DFlash with Qwen3.5 27b though but MiniMax M2.7 is the best I’ve tried so far on 2xGB10

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