Instructions to use GadflyII/MiniMax-M2.1-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GadflyII/MiniMax-M2.1-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="GadflyII/MiniMax-M2.1-NVFP4", 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("GadflyII/MiniMax-M2.1-NVFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("GadflyII/MiniMax-M2.1-NVFP4", 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 GadflyII/MiniMax-M2.1-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GadflyII/MiniMax-M2.1-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GadflyII/MiniMax-M2.1-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GadflyII/MiniMax-M2.1-NVFP4

SGLang

How to use GadflyII/MiniMax-M2.1-NVFP4 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 "GadflyII/MiniMax-M2.1-NVFP4" \
    --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": "GadflyII/MiniMax-M2.1-NVFP4",
		"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 "GadflyII/MiniMax-M2.1-NVFP4" \
        --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": "GadflyII/MiniMax-M2.1-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GadflyII/MiniMax-M2.1-NVFP4 with Docker Model Runner:
```
docker model run hf.co/GadflyII/MiniMax-M2.1-NVFP4
```

Note: Updated for Transformers 5.0.0 release compatibility Jan 26th, 2026.

MiniMax-M2.1-NVFP4

NVFP4 quantized version of MiniMaxAI/MiniMax-M2.1 for efficient inference on NVIDIA Blackwell GPUs.

Model Details

Property	Value
Base Model	MiniMaxAI/MiniMax-M2.1
Architecture	Mixture of Experts (MoE)
Total Parameters	229B
Active Parameters	~45B (8 of 256 experts)
Quantization	NVFP4 (e2m1 format)
Size	131 GB

Quantization Details

Format: NVFP4 with two-level scaling (block-wise FP8 + global FP32)
Scheme: compressed-tensors with nvfp4-pack-quantized format
Target: All linear layers in attention and MoE experts
Group Size: 16

Requirements

NVIDIA Blackwell GPU (RTX 5090, RTX PRO 6000, etc.)
vLLM with flashinfer-cutlass NVFP4 support
~130 GB VRAM (TP=2 recommended for dual GPU setups)

Usage with vLLM

from vllm import LLM, SamplingParams

llm = LLM(
    model="GadflyII/MiniMax-M2.1-NVFP4",
    tensor_parallel_size=2,
    max_model_len=4096,
    gpu_memory_utilization=0.90,
    trust_remote_code=True,
)

sampling_params = SamplingParams(
    temperature=0.7,
    top_p=0.9,
    max_tokens=1024,
)

outputs = llm.generate(["Your prompt here"], sampling_params)
print(outputs[0].outputs[0].text)

Performance

Tested on 2x RTX PRO 6000 Blackwell (96GB each):

Prompt Tokens	Output Tokens	Throughput
~100	100	~73 tok/s
~1260	1000	~72 tok/s

License

Same as base model - see MiniMaxAI/MiniMax-M2.1 for details.

Acknowledgments

MiniMax for the original MiniMax-M2.1 model
vLLM team for NVFP4 quantization support

Downloads last month: 38

Model tree for GadflyII/MiniMax-M2.1-NVFP4

Base model

MiniMaxAI/MiniMax-M2.1

Quantized

(39)

this model