# Ling-3.0-flash

> Ant Group's hybrid-linear Mixture-of-Experts reasoning model, announced 26 July 2026: 124B total parameters with 5.1B active per token, MIT-licensed.

- Maker: Ant Group (inclusionAI)
- Line: Ling (open-weight)
- Canonical page: https://ai-tldr.dev/models/ling-3-0-flash/
- Updated: 2026-08-23

## In short

Ling-3.0-flash is a hybrid reasoning model from inclusionAI, the team behind Ant Group's artificial-general-intelligence programme. Ant Group (inclusionAI) released it on 2 August 2026 as an open-weight model. It has a 256K-token context window. You can use it through OpenRouter.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 256K | [1] |
| Licence | MIT · open weights | [1] |
| Released | 2 August 2026 | [2] |
| Parameters | 124B total · 5.1B activated per token (Mixture-of-Experts) | [1] |

## Sources

1. [Ling-3.0-flash model card (Hugging Face)](https://huggingface.co/inclusionAI/Ling-3.0-flash)
2. [Ant Group unveils Ling-3.0-Flash (press release, July 26, 2026)](https://finance.yahoo.com/technology/ai/articles/ant-group-unveils-ling-3-060000298.html)

## Overview

Ling-3.0-flash is a hybrid reasoning model from inclusionAI, the team behind Ant Group's artificial-general-intelligence programme. Ant Group announced it on 26 July 2026, offered it as a free API on OpenRouter and the Vercel AI Gateway through 3 August 2026, and published the weights to Hugging Face on 2 August 2026 under the MIT license. It is a text-generation model with thinking enabled by default.

The design point is intelligence density rather than raw scale. Ling-3.0-flash runs 124 billion total parameters but activates only 5.1 billion per token — inclusionAI puts that at roughly 12.4% and 8.1% of its own 1T-class Ring-2.6-1T flagship — and says the smaller model matches or outperforms that predecessor across key benchmarks. Ant Group's announcement claims it 'matches or surpasses industry-leading models with two to three times its parameter scale' on core reasoning, instruction-following and long-context benchmarks; the company published those comparisons as chart images rather than as a numeric table, so the individual scores are not transcribed here.

Architecturally the model adopts a native hybrid linear attention stack from the start of pretraining: 35 Kimi Delta Attention (KDA) layers alternating 5:1 with 7 Gated MLA layers, KDA fine-grained diagonal gating, and 1/64 sparse Mixture-of-Experts routing over 512 routed experts plus one shared expert, with 8 experts activated per token. Hidden size is 2,560 across 32 attention heads with a 157,184-token vocabulary. Context was trained on an 8K → 32K → 256K schedule, and inclusionAI's own SGLang recipe serves it at a 262,144-token context window.

The model is aimed at production agent workloads. inclusionAI reports training across more than 10,000 interactive environments covering coding, general and deep-research agent tasks, and native integration with the SGLang HiCache and Mooncake hierarchical caching architecture — physical dual-pools plus a cluster-shared L3 cache — which it credits with cutting time-to-first-token by 60% to over 80% on long-input requests. Its model card names Claude Code, Kilo Code, Qwen Code, Hermes Agent and OpenClaw as harnesses it has been exercised against. The published low-latency recipe runs on four 141GB-class GPUs at tensor-parallel size 4, or eight 80GB cards at tensor-parallel size 8.

## Strengths

- MIT-licensed open weights — free to download, fine-tune, self-host and use commercially
- Activates only 5.1B of 124B parameters per token, keeping serving cost far below dense models of comparable size
- Native hybrid-linear attention (KDA + Gated MLA, 5:1) designed for long-context efficiency from the start of pretraining
- 256K trained context, served at 262,144 tokens in inclusionAI's own SGLang recipe
- Built for agent harnesses: 10,000+ interactive training environments and SGLang HiCache + Mooncake caching, which inclusionAI credits with a 60–80%+ time-to-first-token reduction on long inputs

## Best for

- Production coding and deep-research agents run on self-hosted GPUs under a permissive license
- Long-horizon agent sessions where repeated long-input recomputation dominates latency
- Teams wanting frontier-adjacent reasoning at a fraction of the activated-parameter cost of 1T-class models
- Research on hybrid linear-attention architectures, where the released weights are a reference implementation

## How to access

- [OpenRouter](https://openrouter.ai/inclusionai/ling-3.0-flash:free) — model id `inclusionai/ling-3.0-flash`

## FAQ

### Is Ling-3.0-flash open source?

The weights are published on Hugging Face and ModelScope under the MIT License, so you can download, run, fine-tune and use the model commercially, including self-hosted.

### How many parameters does Ling-3.0-flash use?

124 billion total parameters, of which 5.1 billion are activated per token. inclusionAI describes that as roughly 12.4% of the total parameters and 8.1% of the activated parameters of its 1T-class Ring-2.6-1T flagship.

### What hardware does it need?

inclusionAI's recommended low-latency SGLang recipe runs on four 141GB-class GPUs (H20-3e) or a four-GPU Blackwell node at tensor-parallel size 4, with a 262,144-token context and NEXTN speculative decoding. On 80GB cards such as the H100 or H800 it uses tensor-parallel size 8 with the same flags.

### What is the hybrid-linear architecture?

Ling-3.0 alternates Kimi Delta Attention (KDA) layers with Gated MLA layers in a 5:1 ratio — 35 KDA layers to 7 Gated MLA layers — rather than bolting linear attention on after the fact. inclusionAI adopted it from the start of pretraining and pairs it with KDA fine-grained diagonal gating and 1/64 sparse Mixture-of-Experts routing to cut long-context compute cost.

### How long a context does it support?

The model was trained on an 8K → 32K → 256K context schedule, and inclusionAI's published SGLang launch command serves it with a 262,144-token context window.

## Links

- [Ling-3.0-flash model card (Hugging Face)](https://huggingface.co/inclusionAI/Ling-3.0-flash)
- [Ant Group unveils Ling-3.0-Flash (press release, July 26, 2026)](https://finance.yahoo.com/technology/ai/articles/ant-group-unveils-ling-3-060000298.html)
- [inclusionAI on Hugging Face](https://huggingface.co/inclusionAI)
- [inclusionAI on ModelScope](https://modelscope.cn/organization/inclusionAI)
- [Ling-3.0-flash on OpenRouter](https://openrouter.ai/inclusionai/ling-3.0-flash:free)
- [Ling-3.0-flash SGLang deployment cookbook](https://docs.sglang.io/cookbook/autoregressive/InclusionAI/Ling-3.0-flash)
- [Ling cookbook (inclusionAI/ling-cookbook on GitHub)](https://github.com/inclusionAI/ling-cookbook)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/ling-3-0-flash/
