Model library / inclusionAI
LLaDA2.2-mini is a 16.3 billion-parameter MoE diffusion language model with 128 k token context, supporting Levenshtein editing.
Mixture of experts, count not published
Context length in tokens, as published
Weights at the released precision
Licence declared on the repository
Overview
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
| Repository | inclusionAI/LLaDA2.2-mini |
| Publisher | inclusionAI |
| Published | 5 September 2026 |
| Architecture | LLaDA2MoeModelLM |
| Model type | llada2_moe |
| Parameters | 16,255,643,392 |
| Layers | 20 |
| Hidden size | 2,048 |
| Attention heads | 16, 4 key/value heads |
| Context length | 131,072 tokens |
| Vocabulary | 157,184 tokens |
| Weight format | bfloat16 |
| Licence | apache-2.0 |
Memory
Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.
| Precision | Weights | Notes |
|---|---|---|
| bf16 | 30.3 GiB | Full precision as released |
| fp8 | 15.1 GiB | 8-bit, near-lossless on most models |
| int4 | 7.6 GiB | 4-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
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.
| GPU | Cards needed | Free for cache | Context 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
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 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.
The repository declares apache-2.0. Read the licence text before commercial use: the name alone does not tell you what is allowed.
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.
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
Ling-3.0-flash-Fin is a 127.5 billion-parameter finance-enhanced language model for long-context financial research and analysis.
Ling-3.0-tiny is a 7.9 billion-parameter hybrid MoE language model with 1.3 billion activated parameters per token.
Ling-3.0-flash is a 127.5 B parameter hybrid-linear language model from inclusionAI for reasoning and long-context applications.
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
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.