Instructions to use amd/MiniMax-M2.5-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/MiniMax-M2.5-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="amd/MiniMax-M2.5-NVFP4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("amd/MiniMax-M2.5-NVFP4", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("amd/MiniMax-M2.5-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 Settings

vLLM

How to use amd/MiniMax-M2.5-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/MiniMax-M2.5-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": "amd/MiniMax-M2.5-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/MiniMax-M2.5-NVFP4

SGLang

How to use amd/MiniMax-M2.5-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 "amd/MiniMax-M2.5-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": "amd/MiniMax-M2.5-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 "amd/MiniMax-M2.5-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": "amd/MiniMax-M2.5-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amd/MiniMax-M2.5-NVFP4 with Docker Model Runner:
```
docker model run hf.co/amd/MiniMax-M2.5-NVFP4
```

Model Overview

Model Architecture: MiniMaxM2ForCausalLM
- Input: Text
- Output: Text
Supported Hardware Microarchitecture: AMD MI300/MI350/MI355 (emulation)
ROCm: 7.2.2
PyTorch: 2.10.0
Transformers: 5.2.0
Operating System(s): Linux
Inference Engine: SGLang/vLLM
Model Optimizer: AMD-Quark (v0.12)
- Quantized layers: experts
- Weight quantization: NVFP4, Static
- Activation quantization: NVFP4, Dynamic

Model Quantization

The model was quantized from MiniMaxAI/MiniMax-M2.5 by using AMD-Quark. The weights and activations are quantized to NVFP4.

Quantization scripts:

cd Quark/examples/torch/language_modeling/llm_ptq/
export exclude_layers="lm_head *block_sparse_moe.gate* *self_attn*"
export CUDA_VISIBLE_DEVICES=0,1,2,3
python3 quantize_quark.py \
  --model_dir MiniMaxAI/MiniMax-M2.5 \
  --quant_scheme nvfp4 \
  --num_calib_data 128 \
  --exclude_layers $exclude_layers \
  --model_export hf_format  \
  --trust_remote_code \
  --multi_gpu \
  --output_dir amd/MiniMax-M2.5-NVFP4

For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers.

Deployment

Use with vLLM/SGLang

This model can be deployed efficiently using the vLLM and SGLang backends.

Evaluation

The model was evaluated on gsm8k benchmarks using the vllm framework.

Accuracy

Benchmark	MiniMaxAI/MiniMax-M2.5	amd/MiniMax-M2.5-NVFP4(this model)	Recovery
gsm8k (flexible-extract)	91.51	91.21	99.67%

Reproduction

The GSM8K result was obtained using the lm-evaluation-harness framework, based on the Docker image rocm/vllm-dev:nightly_main_20260603.

Install the lm-eval (Version: 0.4.12) in container first.

pip install lm-eval
pip install lm-eval[api]

Launching server

VLLM_ROCM_USE_AITER=1 vllm serve amd/MiniMax-M2.5-NVFP4/ \
  --tensor-parallel-size 2 \
  --tool-call-parser minimax_m2 \
  --reasoning-parser minimax_m2 \
  --enable-auto-tool-choice \
  --trust-remote-code

Evaluating model in a new terminal

lm_eval \
  --model local-completions \
  --model_args "model=amd/MiniMax-M2.5-NVFP4/,base_url=http://127.0.0.1:8000/v1/completions,tokenized_requests=False,tokenizer_backend=None,num_concurrent=32" \
  --gen_kwargs temperature=1.0,top_p=0.95 \
  --tasks gsm8k \
  --num_fewshot 8 \
  --batch_size 1

License

Downloads last month: 2

Safetensors

Model size

116B params

Tensor type

BF16

F8_E4M3

Model tree for amd/MiniMax-M2.5-NVFP4

Base model

MiniMaxAI/MiniMax-M2.5

Quantized

(66)

this model