Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Xiaomi MiMo - Mixture of experts - verified

Run MiMo-V2.6-Pro-RL locally

MiMo-V2.6-Pro-RL is a 1.02T mixture-of-experts (42B active) model from Xiaomi MiMo with a 1.05M-token context window, released under MIT (commercial use is allowed); the smallest listed download is 554.2 GB, the MXFP4 GGUF build from ggml-org/MiMo-V2.6-Pro-RL-GGUF.

Official weights: XiaomiMiMo/MiMo-V2.6-Pro-RL - modalities: text, image, video, audio

Total params
1.02T
Active params
42B
Context
1.05M
Smallest download
554.2 GB

Fits in

Smallest download at most 85% of memory

None of the tiers here. The smallest listed download is 554.2 GB, more than 85% of 256 GB.

Downloads

The official weights and every quantization listed for this model, with file sizes from Hugging Face.

MiMo-V2.6-Pro-RL downloads and file sizes
DownloadFormatSizeRepo
Official weightsMXFP4566.0 GBXiaomiMiMo/MiMo-V2.6-Pro-RL
MXFP4Smallest listedGGUF554.2 GBggml-org/MiMo-V2.6-Pro-RL-GGUF

GB is decimal: 1 GB = 10^9 bytes. Add memory for the context and the operating system on top of the file size.

Run it

Copied verbatim from the page linked under each command. Server commands from model cards often assume a multi-GPU node; check the flags before you run them.

vLLM

Terminal
vllm serve XiaomiMiMo/MiMo-V2.6-Pro-RL \
  --tensor-parallel-size 8 \
  --trust-remote-code \
  --gpu-memory-utilization 0.95 \
  --max-model-len auto \
  --reasoning-parser mimo \
  --tool-call-parser mimo \
  --enable-auto-tool-choice \
  --generation-config vllm

Source: huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL

Not sure which runtime to use? Compare local LLM runtimes by platform, API and features.

License

License
MITmit
Commercial use
Commercial use: YesCommercial use is allowed.
Gated download
No. The files download directly.

Worth knowing

The official weights store experts in MXFP4 under an FP8 quantization config, and weightsBytes counts only the root safetensors, excluding the audio tokenizer and draft-model subfolders.

Released (per the announcement).

API pricing and specsHosted prices per 1M tokens for MiMo-V2.6-Pro-RL, if you would rather not run it yourself.

FAQ

How big is the MiMo-V2.6-Pro-RL download?

The official MXFP4 weights in XiaomiMiMo/MiMo-V2.6-Pro-RL are 566.0 GB. The smallest listed download is 554.2 GB, the MXFP4 GGUF build from ggml-org/MiMo-V2.6-Pro-RL-GGUF. Plan for more memory than the file size: the context (KV cache) and the operating system need room too.

Can I use MiMo-V2.6-Pro-RL commercially?

MiMo-V2.6-Pro-RL is released under MIT, and commercial use is allowed. The license text is at https://opensource.org/licenses/MIT.

How much memory do I need for MiMo-V2.6-Pro-RL?

Its smallest listed download is 554.2 GB, more than 85% of 256 GB, so it needs a multi-GPU server or a machine with more memory than the largest tier here.

What is the context length of MiMo-V2.6-Pro-RL?

1,048,576 tokens. A longer context needs more memory for the KV cache, so you can run with a shorter one when memory is tight.

Sources

Last verified from the pages below.

Newsletter

New open weights, every week

One email per week. New model releases, open-weight drops and what they mean for what you build.

Keep exploring

Best local AI models

Our curated picks by hardware tier, with benchmarks and the reasoning.

Model API pricing and specs

First-party prices per 1M tokens when you would rather call an API.

AI benchmark leaderboards

Sourced scores, for when you need to compare quality.

Setup guides

Point your coding tools at the model you picked.