Instructions to use amd/MiniMax-M2.5-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/MiniMax-M2.5-MXFP4 with Transformers:

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

pipe = pipeline("text-generation", model="amd/MiniMax-M2.5-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("amd/MiniMax-M2.5-MXFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("amd/MiniMax-M2.5-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 amd/MiniMax-M2.5-MXFP4 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-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": "amd/MiniMax-M2.5-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/MiniMax-M2.5-MXFP4

SGLang

How to use amd/MiniMax-M2.5-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 "amd/MiniMax-M2.5-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": "amd/MiniMax-M2.5-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 "amd/MiniMax-M2.5-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": "amd/MiniMax-M2.5-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amd/MiniMax-M2.5-MXFP4 with Docker Model Runner:
```
docker model run hf.co/amd/MiniMax-M2.5-MXFP4
```

Xiao-AMD commited on Feb 23

Commit

f8a517c

verified ·

1 Parent(s): 7a9dbbf

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -24

README.md CHANGED Viewed

@@ -77,35 +77,26 @@ The model was evaluated on gsm8k benchmarks using the [vllm](https://github.com/
 ### Reproduction
-The GSM8K results were obtained using the vLLM framework, based on the Docker image `rocm/vllm:rocm7.0.0_vllm_0.11.2_20251210`, and vLLM is installed inside the container with fixes applied for model support.
-#### Preparation in container
-```
-# Reinstall vLLM
-pip uninstall vllm -y
-git clone https://github.com/vllm-project/vllm.git
-cd vllm
-git checkout v0.13.0
-pip install -r requirements/rocm.txt
-python setup.py develop
-cd ..
 ```
-#### Launching server
-```
-VLLM_ROCM_USE_AITER=1 \
-VLLM_DISABLE_COMPILE_CACHE=1 \
-vllm serve "$MODEL" \
-    --tensor-parallel-size 4 \
-    --trust-remote-code \
-    --max-model-len 32768 \
-    --port 8899
-```
-#### Evaluating model in a new terminal
-```
-python vllm/tests/evals/gsm8k/gsm8k_eval.py --host http://127.0.0.1 --port 8899 --num-questions 1000 --save-results logs
 ```

 ### Reproduction
+The GSM8K results were obtained using the lm-eval framework, based on the Docker image `rocm/vllm-dev:nightly`.
+#### Evaluating model in a new terminal
 ```
+export VLLM_ROCM_USE_AITER=1
+export model_dir_fp4=MiniMaxAI/MiniMax-M2.5-mxfp4/
+log_file=minimax25-lm_eval_gsm8k_mxfp4.txt
+lm_eval --model vllm --model_args pretrained=$model_dir_fp4,enforce_eager=True,trust_remote_code=True,max_model_len=16384 \
+        --gen_kwargs temperature=1.0,top_p=0.95,top_k=40 \
+        --tasks gsm8k  --num_fewshot 8 2>&1 | tee $log_file
+export model_dir=MiniMaxAI/MiniMax-M2.5/
+log_file=minimax25-lm_eval_gsm8k.txt
+lm_eval --model vllm --model_args pretrained=$model_dir,enforce_eager=True,tensor_parallel_size=8,trust_remote_code=True,max_model_len=16384 \
+        --gen_kwargs temperature=0.8,top_p=0.95,top_k=40 \
+        --tasks gsm8k  --num_fewshot 8 2>&1 | tee $log_file
 ```