Aiqre

Model library / 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.

7.9B

Parameters in total

131,072

Context length in tokens, as published

15 GiB

Weights at the released precision

mit

Licence declared on the repository

Overview

What this model is.

Ling-3.0-tiny is a lightweight hybrid-reasoning model released by inclusionAI. It combines alternating KDA and MLA layers with a sparse MoE feed-forward network of 128 experts, activating eight routed experts and one shared expert per token. The publisher positions it for fast responses, multi-step reasoning, and agentic tasks on local or edge hardware.

The model contains 7.9 billion total parameters but only 1.3 billion are active per token, reducing compute load. It supports a 131,072-token context window and is distributed under the MIT licence. Weights are provided in bfloat16 format, with optional FP8 and INT4 variants for diverse deployment environments.

Specification

The published shape.

RepositoryinclusionAI/Ling-3.0-tiny
PublisherinclusionAI
Published10 August 2026
ArchitectureBailingMoeV3ForCausalLM
Model typebailing_hybrid
Parameters7,893,392,800
Layers24
Hidden size1,536
Attention heads16, 16 key/value heads
Context length131,072 tokens
Vocabulary157,184 tokens
Weight formatbfloat16
Licencemit

Memory

How much VRAM the weights need.

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

PrecisionWeightsNotes
bf1614.7 GiBFull precision as released
fp87.4 GiB8-bit, near-lossless on most models
int43.7 GiB4-bit, smallest footprint

The cache costs 192 KiB per token at 16-bit, so the full 131,072-token context of one request needs about 24.0 GiB. Concurrency multiplies that number, not the weights.

That figure is an upper bound: this model uses compressed key-value attention, so the real cache is a fraction of the figure above.

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 1 4.4 GiB about 24,015 tokens
RTX 5090 32GB 1 11.6 GiB about 63,336 tokens
L40S 48GB 1 26.0 GiB the full 131,072 tokens
A100 80GB 1 54.8 GiB the full 131,072 tokens
H100 80GB 1 54.8 GiB the full 131,072 tokens
RTX PRO 6000 96GB 1 69.2 GiB the full 131,072 tokens
H200 141GB 1 109.7 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/Ling-3.0-tiny \
  --max-model-len 20480 \
  --gpu-memory-utilization 0.90

Questions

The things people ask about this model.

How much GPU memory does Ling-3.0-tiny need?

The weights take about 15 GiB at the released precision. That fits on one RTX 4090 24GB, which leaves roughly 4 GiB for the key-value cache.

What licence does Ling-3.0-tiny use?

The repository declares mit. 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/LLaDA2.2-mini

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

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-flash

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

zgcagi/ZGCM-1-7B

ZGCM-1 is a 7.4 billion-parameter dense language model designed for mathematical reasoning and tool-assisted search.

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.