Instructions to use hf-internal-testing/MiniMax-M2-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/MiniMax-M2-Small with Transformers:

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

pipe = pipeline("text-generation", model="hf-internal-testing/MiniMax-M2-Small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/MiniMax-M2-Small")
model = AutoModelForCausalLM.from_pretrained("hf-internal-testing/MiniMax-M2-Small")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/MiniMax-M2-Small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hf-internal-testing/MiniMax-M2-Small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/MiniMax-M2-Small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hf-internal-testing/MiniMax-M2-Small

SGLang

How to use hf-internal-testing/MiniMax-M2-Small 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 "hf-internal-testing/MiniMax-M2-Small" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/MiniMax-M2-Small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "hf-internal-testing/MiniMax-M2-Small" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/MiniMax-M2-Small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/MiniMax-M2-Small with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/MiniMax-M2-Small
```

AntonV HF Staff commited on Dec 11, 2025

Commit

0831be1

verified ·

1 Parent(s): eccb1b6

Upload MiniMaxM2ForCausalLM

Browse files

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -15,7 +15,7 @@
   "model_type": "minimax_m2",
   "num_attention_heads": 2,
   "num_experts_per_tok": 2,
-  "num_hidden_layers": 2,
   "num_key_value_heads": 1,
   "num_local_experts": 8,
   "output_router_logits": false,

   "model_type": "minimax_m2",
   "num_attention_heads": 2,
   "num_experts_per_tok": 2,
+  "num_hidden_layers": 5,
   "num_key_value_heads": 1,
   "num_local_experts": 8,
   "output_router_logits": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a2a1ce27a61455d3d40e607ab450ed7a3d8aafd5cc436fe6f84ddb023578c9
-size 212762968

 version https://git-lfs.github.com/spec/v1
+oid sha256:5f10fce0fe3e5c7ee3626dd2f0270a5e0a540f59a70d2c6d6ed28a7f53cccf81
+size 224607248