Model reference · open weights

LLaDA2.0-Uni

LLaDA2.0-Uni is an open-weight language model from inclusionAI, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

LLMs inclusionAI 2 variants 5k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What LLaDA2.0-Uni is

[📑 Technical Report ]   [🌐 Github ]  [🤗 FP8 Version ] Model Capabilities LLaDA2.0-Uni is a unified diffusion Large Language Model (dLLM) based on Mixture-of-Experts (MoE) that seamlessly integrates multimodal understanding and generation within a single model. It supports: - 🖼️ Text-to-Image Generation — high-fidelity image synthesis with optional thinking/reasoning. - 🔍 Image Understanding — visual question answering, image captioning, document understanding, etc. - ✏️ Image Editing — instruction-based editing with single or multi-reference support. - 🎨 Interleaved Generation and Reasoning — provide preliminary support for interleaved generation and unlock advanced interleaved reasoning. - ⚡ Sprint Acceleration — KV cache reuse and adaptive unmasking for faster inference. Model Architecture - Unified dLLM-MoE Backbone: Unifies multimodal understanding and generation into a simple Mask Token Prediction paradigm. - Discrete Semantic Tokenizer: Utilizes SigLIP-VQ to convert visual inputs into discrete semantic tokens, significantly enhancing multimodal understanding. - Efficient Diffusion Decoder: Pairs discrete tokens with a specialized diffusion decoder for high-fidelity generation, enabling rapid 8-step inference via distillation. Evaluation Results Quick Start Note: Full installation instructions and CLI scripts are available in the GitHub repository. ⚙️ Installation 1. Create a conda environment 2. Install PyTorch (CUDA 12.4) 3. Install Flash Attention 2 (required for efficient inference) 4. Install remaining dependencies 🌟 Text-to-Image Generation [!Note] 💡 Faster decoding — Use the decoder-turbo (distilled decoder) for ~10× faster image decoding (8 steps instead of 50) with minimal quality loss: python image = decodevqtokens( result["tokenids"], result["h"], result["w"], modelpath, "cuda", numsteps=8, decodemode="decoder-turbo", ) 🌟 Text-to-Image Generation with Thinking 🌟 Image Understanding 🌟 Image Editing 🌟 SPRINT Acceleration SPRINT accelerates inference by combining KV cache reuse, adaptive unmasking, and threshold-based batch acceptance: - KV Cache Reuse & Pruning: The prefix KV cache is computed once during warmup steps, then optionally pru

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerinclusionAI
TypeLanguage models
Parameters (lead)16.3B
Context8k tokens
Variants2
Runs withtransformers
Based oninclusionAI/LLaDA2.0-mini
Released2026-04-22
Popularity5k downloads / month
Likes250
LicenceOpen weights

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
LLaDA2.0-Uni16.3BBF16~37.5 GBWeights ↗
LLaDA2.0-Uni-FP816.3BFP8~18.8 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys llada2-0-uni for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (llada2-0-uni 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":"llada2-0-uni","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Languages

en

Tags

transformers diffusers safetensors llada2_moe feature-extraction multimodal image-generation image-understanding image-editing diffusion moe text-to-image any-to-any custom_code

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want LLaDA2.0-Uni on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More language models

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