What are the hardware requirements for LLaDA2.0 Flash Preview?

LLaDA2.0 Flash Preview requires approximately 205.9 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LLaDA2.0 Flash Preview and how large is it?

LLaDA2.0 Flash Preview is developed by inclusionAI, a model with 102.9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate LLaDA2.0 Flash Preview?

LLaDA2.0 Flash Preview is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LLaDA2.0 Flash Preview by inclusionAI — VRAM 205.9GB, 16K context

Name: LLaDA2.0 Flash Preview
Author: inclusionAI

LLaDA2.0 Flash Preview is an open-source language model by inclusionAI. Features: 102.9b LLM, VRAM: 205.9GB, Context: 16K, License: apache-2.0, LLM Explorer Score: 0.21.

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-flash-preview

LLaDA2.0 Flash Preview Parameters and Internals

LLM Name	LLaDA2.0 Flash Preview
Repository 🤗	https://huggingface.co/inclusionAI/LLaDA2.0-flash-preview
Model Size	102.9b
Required VRAM	205.9 GB
Updated	2026-07-27
Maintainer	inclusionAI
Model Type	llada2_moe
Model Files	5.0 GB: 1-of-42 5.0 GB: 2-of-42 5.0 GB: 3-of-42 5.0 GB: 4-of-42 4.4 GB: 5-of-42 5.0 GB: 6-of-42 5.0 GB: 7-of-42 5.0 GB: 8-of-42 5.0 GB: 9-of-42 5.0 GB: 10-of-42 5.0 GB: 11-of-42 5.0 GB: 12-of-42 5.0 GB: 13-of-42 5.0 GB: 14-of-42 5.0 GB: 15-of-42 5.0 GB: 16-of-42 5.0 GB: 17-of-42 5.0 GB: 18-of-42 5.0 GB: 19-of-42 5.0 GB: 20-of-42 5.0 GB: 21-of-42 5.0 GB: 22-of-42 5.0 GB: 23-of-42 5.0 GB: 24-of-42 5.0 GB: 25-of-42 5.0 GB: 26-of-42 5.0 GB: 27-of-42 5.0 GB: 28-of-42 5.0 GB: 29-of-42 5.0 GB: 30-of-42 5.0 GB: 31-of-42 5.0 GB: 32-of-42 5.0 GB: 33-of-42 5.0 GB: 34-of-42 5.0 GB: 35-of-42 5.0 GB: 36-of-42 5.0 GB: 37-of-42 5.0 GB: 38-of-42 5.0 GB: 39-of-42 5.0 GB: 40-of-42 5.0 GB: 41-of-42 1.5 GB: 42-of-42
Model Architecture	LLaDA2MoeModelLM
License	apache-2.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.52.3
Vocabulary Size	157184
Torch Data Type	bfloat16

Rank the LLaDA2.0 Flash Preview capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the LLaDA2.0 Flash Preview

Model	Likes	Downloads	VRAM
LLaDA2.0 Flash Preview 4bit	3	12	57 GB

Best Alternatives to LLaDA2.0 Flash Preview

Best Alternatives	Context / RAM	Downloads	Likes
LLaDA2.2 Flash	128K / 204.5 GB	328	57
LLaDA2.1 Flash	32K / 204.5 GB	29820	93
LLaDA2.0 Flash	32K / 206 GB	518	69
LLaDA2.0 Flash CAP	32K / 206 GB	65	9
LLaDA2.2 Flash OptiQ 2bit	128K / 38.9 GB	61	3
LLaDA2.0 Flash 4bit	32K / 57.8 GB	18	3
LLaDA2.0 Flash 8bit	32K / 109.3 GB	11	1
LLaDA2.0 Flash Preview 4bit	16K / 57.8 GB	12	3

Note: green Score (e.g. "73.2") means that the model is better than inclusionAI/LLaDA2.0-flash-preview.