Aiqre

Model library / 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.

127.5B

Mixture of experts, count not published

262,144

Context length in tokens, as published

237 GiB

Weights at the released precision

mit

Licence declared on the repository

Overview

What this model is.

Ling-3.0-flash-Fin is a finance-focused extension of the Ant Ling family, trained on high-quality financial data to support end-to-end research, source-grounded search, multi-document reasoning, valuation modelling and spreadsheet workflows. The publisher, inclusionAI, describes it as suitable for agent-driven financial tasks that require accurate source citation and tool-intensive operations.

The model contains 127.5 billion parameters, with 5.1 billion activated at inference, and supports a 262,144-token context window. It is released under the MIT licence in bfloat16 format and uses a BailingMoeV3ForCausalLM architecture with mixture-of-experts. Compatibility with SGLang and vLLM runtimes enables deployment on standard inference stacks.

Specification

The published shape.

RepositoryinclusionAI/Ling-3.0-flash-Fin
PublisherinclusionAI
Published3 September 2026
ArchitectureBailingMoeV3ForCausalLM
Model typebailing_hybrid
Parameters127,486,405,600
Layers42
Hidden size2,560
Attention heads32, 32 key/value heads
Context length262,144 tokens
Vocabulary157,184 tokens
Weight formatbfloat16
Licencemit
Base modelinclusionAI/Ling-3.0-flash

Memory

How much VRAM the weights need.

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

PrecisionWeightsNotes
bf16237.5 GiBFull precision as released
fp8118.7 GiB8-bit, near-lossless on most models
int459.4 GiB4-bit, smallest footprint

The cache costs 672 KiB per token at 16-bit, so the full 262,144-token context of one request needs about 168.0 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 more than 8
RTX 5090 32GB more than 8
L40S 48GB 8 88.1 GiB about 137,528 tokens
A100 80GB 4 40.5 GiB about 63,254 tokens
H100 80GB 4 40.5 GiB about 63,254 tokens
RTX PRO 6000 96GB 4 98.1 GiB about 153,132 tokens
H200 141GB 2 11.3 GiB about 17,691 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-flash-Fin \
  --tensor-parallel-size 8 \
  --max-model-len 135168 \
  --gpu-memory-utilization 0.90

Questions

The things people ask about this model.

How much GPU memory does Ling-3.0-flash-Fin need?

The weights take about 237 GiB at the released precision. No single card in the table above holds that, so it needs several GPUs or a lower precision.

What licence does Ling-3.0-flash-Fin 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 262,144 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-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.

poolside/Laguna-S-2.1

Laguna S 2.1 is a 118 billion-parameter mixture-of-experts model for agentic coding with long-context support.

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.