Open weights answer one question: can you download a model checkpoint and run it? Open source is a wider question about the code, data, tools, and permissions around that checkpoint. Xiaomi’s September 22, 2026 MiMo-V2.6 release calls the series “fully open-source.” Read that as an artifact inventory, not proof that every training input or production dependency is public.

Four layers that people collapse

LayerWhat it meansWhat a release may let you do
Weights and checkpointLearned tensor values, usually shipped with configuration and tokenizer files. A checkpoint is a saved point in training.Load a compatible model, run inference, and sometimes fine-tune it under its license.
Model and training codeThe architecture implementation, loader, optimizer, RL loop, and scripts.Inspect or modify the software and try a recipe. Its license can differ from the weights.
Data, environments, and gradersPrompts or task rows, sandboxes, Docker images, tests, rubrics, and reward code that turn an action into feedback.Study an RL task and run a bounded experiment. This is not the same as releasing the entire pretraining corpus.
ReproducibilityEnough versioned inputs, settings, compute, dependencies, and evaluation detail to rerun a result.Check a claim or reproduce part of a result. “The code is public” alone does not guarantee identical scores.

For agent RL, keep the pieces separate. The model produces tokens and actions. A harness supplies the tool protocol, prompt, context, and control loop. An environment is the repository, browser, or sandbox where actions have consequences. A grader runs tests or a rubric and emits a reward. Changing one can change the result even with identical weights.

MiMo V2.6 as a worked example

The MiMo V2.6 Hugging Face collection lists Pro-RL, Flash-RL, and Distill-Qwen-9B. Their cards label the model repositories MIT. That does not automatically license a dataset, Docker image, or related code repository.

Pro and Flash are sparse Mixture-of-Experts models. Their cards report 1.02T total / 42B activated parameters for Pro and 309B total / 15B activated parameters for Flash, with 1M-token context and text, image, video, and audio inputs. “Activated” means the router selects only some experts for a token. Other experts still have to be stored, so active parameters are a compute hint, not a memory estimate; runtime buffers, KV cache, and multimodal components add demand.

The smaller 9B card says it is a Qwen3.5-9B model supervised-fine-tuned on MiMo-generated data and released as an SFT starting point for agentic RL research. It is useful for studying the public recipe. It is not a small post-RL equivalent of Flash or Pro, and the release does not include a smaller Flash/Pro post-RL checkpoint.

Xiaomi also publishes an RL dataset with 7,780 rows and an Apache-2.0 label. The linked verl training fork and uni-agent are Apache-2.0; the mimoagent harness is MIT. These are useful building blocks, but do not establish that the full pretraining data, every production grader, or the exact six-day run is reproducible on a personal machine.

What can you do with the download?

Your goalStart withRealistic conclusion
Run the modelA model-card checkpoint, tokenizer/config, and a supported runtimeYou can attempt compatible inference if your hardware and runtime support the artifact.
Adapt itWeights, code, and your own permitted dataYou can make a derivative or fine-tune; check every license and dependency first.
Learn agent RLThe 9B SFT checkpoint, RL dataset, linked Docker image, and public training codeYou can inspect and rerun a bounded research setup, then compare your own measurements.
Verify a headlineThe technical report, model cards, task definitions, and evaluation settingsYou can audit what Xiaomi reports; vendor numbers are not an AIHackers-owned benchmark.

Use the MiMo model guide for access and model choice, how to read an RL training dashboard for chart fields, the local LLM guide for hardware, and the cost-saving playbook for infrastructure and review costs.

Open weights give you control over a checkpoint; open code and environments let you inspect and extend the surrounding system. Reproducibility is the stronger claim: make it only when released versions, inputs, graders, compute assumptions, and evaluation support it.

AIHackers training reproduction: not-run. Public resources were inspected; no models or training environments were executed for this guide.

Sources checked