Instructions to use XiaomiMiMo/MiMo-V2.6-Pro-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use XiaomiMiMo/MiMo-V2.6-Pro-RL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="XiaomiMiMo/MiMo-V2.6-Pro-RL", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("XiaomiMiMo/MiMo-V2.6-Pro-RL", trust_remote_code=True, device_map="auto") - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use XiaomiMiMo/MiMo-V2.6-Pro-RL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "XiaomiMiMo/MiMo-V2.6-Pro-RL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "XiaomiMiMo/MiMo-V2.6-Pro-RL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
- SGLang
How to use XiaomiMiMo/MiMo-V2.6-Pro-RL 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 "XiaomiMiMo/MiMo-V2.6-Pro-RL" \ --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": "XiaomiMiMo/MiMo-V2.6-Pro-RL", "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 "XiaomiMiMo/MiMo-V2.6-Pro-RL" \ --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": "XiaomiMiMo/MiMo-V2.6-Pro-RL", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use XiaomiMiMo/MiMo-V2.6-Pro-RL with Docker Model Runner:
docker model run hf.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
Native quant?
Are these new models natively q4?
Que 8
Que 8
How would it be q8 if the total download size is half of the param count?
It's mixed, and the experts are effectively 4-bit. From quantization_config in config.json:
quant_method: fp8,fmt: e4m3,weight_block_size: [128, 128]โ the dense/attention/shared weights are FP8 with 128ร128 block scales (theo_projlayers are inignored_layers, so those stay BF16)store_dtype: mxfp4,mxfp4_block_size: 32โ the routed expert weights are stored as MXFP4: 4-bit E2M1 values plus one 8-bit scale per 32 weights = 4.25 bits/weight
That's why the download is about half the param count. The U8 tensors hold 1.000T expert weights. At 4.25 bits that works out to 1.000T ร 17/32 โ 531 GB. Add ~10.6B BF16 params (21 GB) and 13.4B FP8 params (13 GB) and you get โ 566 GB, which matches the file listing. Averaged over ~1.024T params, that's ~4.4 bits/weight.
So "q8" is right only for the non-expert part. The bulk of the model is MXFP4, the same scheme gpt-oss uses. For memory planning, that's ~527 GiB of weights before any KV cache.