LLaDA2.0 Mini Preview is an open-source language model by inclusionAI. Features: 16.3b LLM, VRAM: 32.5GB, Context: 8K, License: apache-2.0.
Arxiv:2512.15745 Conversational Custom code Diffusion Dllm Llada2 moe Region:us Safetensors Sharded Tensorflow Text generation
Model Card on HF 🤗: https://huggingface.co/inclusionAI/LLaDA2.0-mini-preview
LLaDA2.0 Mini Preview Parameters and Internals
| LLM Name | LLaDA2.0 Mini Preview |
| Repository 🤗 | https://huggingface.co/inclusionAI/LLaDA2.0-mini-preview |
| Model Size | 16.3b |
| Required VRAM | 32.5 GB |
| Updated | 2026-03-27 |
| Maintainer | inclusionAI |
| Model Type | llada2_moe |
| Model Files | |
| Model Architecture | LLaDA2MoeModelLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.52.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 157184 |
| Torch Data Type | bfloat16 |
Rank the LLaDA2.0 Mini Preview Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51648 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260327b