AxForge
Sign in Get started

Model reference · open weights

MMaDA-MixCoT

Available as managed deployment LLMs Gen-Verse Omni (any→any) 1 variants 1k dl/mo

MMaDA-MixCoT is an open-weight language model from Gen-Verse. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Request deployment All language models

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byGen-Verse
TypeLanguage models
TaskOmni (any→any)
Parameters (lead)8.1B
Runs withtransformers
Released2025-06-01
Popularity1k downloads / month
LicenceOpen weights

About

What MMaDA-MixCoT is

We introduce MMaDA, a novel class of multimodal diffusion foundation models designed to achieve superior performance across diverse domains such as textual reasoning, multimodal understanding, and text-to-image generation. MMaDA is distinguished by three key innovations:

  1. MMaDA adopts a unified diffusion architecture with a shared probabilistic formulation and a modality-agnostic design, eliminating the need for modality-specific components.
  2. MMaDA introduces a mixed long chain-of-thought (CoT) fine-tuning strategy that curates a unified CoT format across modalities.
  3. MMaDA adopts a unified policy-gradient-based RL algorithm, which we call UniGRPO, tailored for diffusion foundation models. Utilizing diversified reward modeling, UniGRPO unifies post-training across both reasoning and generation tasks, ensuring consistent performance improvements.

Compared to MMaDA-8B-Base, MMaDA-8B-MixCoT exhibits better instruction-following capabilities and more stable CoT generation performance.

Read the full model card

Paper | Code | Demo

Citation

@article{yang2025mmada,
  title={MMaDA: Multimodal Large Diffusion Language Models},
  author={Yang, Ling and Tian, Ye and Li, Bowen and Zhang, Xinchen and Shen, Ke and Tong, Yunhai and Wang, Mengdi},
  journal={arXiv preprint arXiv:2505.15809},
  year={2025}
}

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys mmada-mixcot for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (mmada-mixcot below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mmada-mixcot","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

Get API access
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms