Aiqre

Model library / inclusionAI

LLaDA2.2-mini

LLaDA2.2-mini is a 16.3 billion-parameter MoE diffusion language model with 128 k token context, supporting Levenshtein editing.

16.3B

Mixture of experts, count not published

131,072

Context length in tokens, as published

30 GiB

Weights at the released precision

apache-2.0

Licence declared on the repository

Overview

What this model is.

LLaDA2.2-mini is a lightweight variant of the agentic diffusion language model series, built on the LLaDA2.0-mini architecture. InclusionAI describes it as enabling long-context tool calling, multi-turn interaction and error correction through Levenshtein editing control tokens (DELETE, INSERT) and a block-level MoE routing mechanism.

In practice the model contains 16.3 billion total parameters, of which about 1.4 billion are active per inference step, and supports a 131 072 token context window. It is distributed under the Apache-2.0 licence and stored in bfloat16 format, making it suitable for deployment on hardware that can handle large context windows and MoE inference.

Specification

The published shape.

RepositoryinclusionAI/LLaDA2.2-mini
PublisherinclusionAI
Published5 September 2026
ArchitectureLLaDA2MoeModelLM
Model typellada2_moe
Parameters16,255,643,392
Layers20
Hidden size2,048
Attention heads16, 4 key/value heads
Context length131,072 tokens
Vocabulary157,184 tokens
Weight formatbfloat16
Licenceapache-2.0

Memory

How much VRAM the weights need.

Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.

PrecisionWeightsNotes
bf1630.3 GiBFull precision as released
fp815.1 GiB8-bit, near-lossless on most models
int47.6 GiB4-bit, smallest footprint

The cache costs 40 KiB per token at 16-bit, so the full 131,072-token context of one request needs about 5.0 GiB. Concurrency multiplies that number, not the weights.

Hardware

Which card runs it.

At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.

GPUCards neededFree for cacheContext it holds
RTX 4090 24GB 2 7.9 GiB the full 131,072 tokens
RTX 5090 32GB 2 22.3 GiB the full 131,072 tokens
L40S 48GB 1 10.4 GiB the full 131,072 tokens
A100 80GB 1 39.2 GiB the full 131,072 tokens
H100 80GB 1 39.2 GiB the full 131,072 tokens
RTX PRO 6000 96GB 1 53.6 GiB the full 131,072 tokens
H200 141GB 1 94.1 GiB the full 131,072 tokens

Serving

Running it yourself.

A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.

vllm serve inclusionAI/LLaDA2.2-mini \
  --max-model-len 131072 \
  --gpu-memory-utilization 0.90

Questions

The things people ask about this model.

How much GPU memory does LLaDA2.2-mini need?

The weights take about 30 GiB at the released precision. That fits on one L40S 48GB, which leaves roughly 10 GiB for the key-value cache.

What licence does LLaDA2.2-mini use?

The repository declares apache-2.0. Read the licence text before commercial use: the name alone does not tell you what is allowed.

How long a context does it support?

The configuration allows 131,072 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.

Can I use it through an API instead of hosting it?

This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.

Also in the library

Related models.

inclusionAI/Ling-3.0-flash-Fin

Ling-3.0-flash-Fin is a 127.5 billion-parameter finance-enhanced language model for long-context financial research and analysis.

inclusionAI/Ling-3.0-tiny

Ling-3.0-tiny is a 7.9 billion-parameter hybrid MoE language model with 1.3 billion activated parameters per token.

inclusionAI/Ling-3.0-flash

Ling-3.0-flash is a 127.5 B parameter hybrid-linear language model from inclusionAI for reasoning and long-context applications.

Gryphe/Pantheon-Reasoning-26B-A4B-1.1-V2

Pantheon-Reasoning-26B-A4B-1.1-V2 is a 26.5 billion-parameter Gemma-4 mixture-of-experts finetune aimed at role-play scenarios, i…

Hosting

Want this model on a dedicated EU GPU?

Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.