How is Ling-3.0-flash different from other 100B+ open-weight models?

Ling-3.0-flash mixes linear attention (Kimi Delta) with standard attention in a 5:1 ratio, trained that way from scratch. Ant Group says this cuts Time-To-First-Token by 60-80% on long prompts when paired with SGLang HiCache and Mooncake caching. Combined with its 5.1B active params, it targets long-context agent workloads without flagship compute cost.

What benchmark scores has Ant Group published for Ling-3.0-flash?

Ant Group's model card reports 56.6 on SWE-Bench Pro, 93.2 on AIME 2026, 87 on HMMT February 2026, and 72.4 on SWE-Bench Multilingual. All figures come from the release page — no independent audit exists yet at open-weights launch.

How do you run Ling-3.0-flash locally?

Ling-3.0-flash runs on SGLang or a custom vLLM fork published by inclusionAI. Recommended sampling is temperature 0.6, top_p 0.95, top_k 20. The full BF16 checkpoint is 255GB; an FP8 variant at 128GB is also on Hugging Face for smaller GPU setups.

Was Ling-3.0-flash available before the open-weights release?

Yes, but only through hosted APIs. From July 23 to August 3, 2026 Ling-3.0-flash was free on OpenRouter, Vercel AI Gateway and Kilo. Ant Group open-sourced the weights on August 5 under an MIT license, so anyone can now self-host or fine-tune.

Ant Group (inclusionAI) · 2026-08-05 · major

Ling-3.0-flash — Ant Group opens 124B MoE with 5.1B active params under MIT

Ling-3.0-flash is Ant Group's 124B open-weight MoE with only 5.1B params active per token. Hybrid Kimi Delta + Gated MLA attention, 56.6 on SWE-Bench Pro, MIT-licensed weights on Hugging Face.

Hugging Face model card thumbnail for inclusionAI Ling-3.0-flash

A 124B open-weight MoE that runs like a 5B model — Ant Group ships it under MIT.

Key specs

Parameters	124B
Active params	5.1B
Swe bench pro	56.6
Aime 2026	93.2

Quick facts

Maker	Ant Group (inclusionAI)
Total parameters	124B
Active per token	5.1B
Architecture	MoE (512 experts, 8 active + 1 shared)
Attention	Hybrid — 35 KDA + 7 Gated MLA layers (5:1)
Context window	256K tokens
License	MIT

What is it?

Ling-3.0-flash is Ant Group's newest open-weight MoE model, released by their inclusionAI arm. It has 124 billion total parameters but activates only 5.1 billion per token, so it runs closer to a 5B model on hardware while pulling from a much larger expert pool. Weights landed on Hugging Face on August 5, 2026 under an MIT license.

How does it work?

The model swaps most standard attention for a hybrid stack — 35 layers of Kimi Delta Attention (a linear attention variant) paired with 7 layers of Gated Multi-head Latent Attention in a 5:1 pattern. The MoE routes each token to 8 of 512 experts plus one shared expert. Ling-3.0-flash was trained in context stages of 8K, then 32K, then 256K tokens.

Why does it matter?

The hybrid linear attention combined with SGLang HiCache and Mooncake tiered caching cuts Time-To-First-Token by 60-80% on long inputs, so an agent scanning a large codebase stays snappy. With just 5.1B active params, teams can self-host a strong reasoning model without paying flagship-scale compute costs.

Who is it for?

teams self-hosting a strong coding and reasoning model

Frequently asked questions

How is Ling-3.0-flash different from other 100B+ open-weight models?: Ling-3.0-flash mixes linear attention (Kimi Delta) with standard attention in a 5:1 ratio, trained that way from scratch. Ant Group says this cuts Time-To-First-Token by 60-80% on long prompts when paired with SGLang HiCache and Mooncake caching. Combined with its 5.1B active params, it targets long-context agent workloads without flagship compute cost.
What benchmark scores has Ant Group published for Ling-3.0-flash?: Ant Group's model card reports 56.6 on SWE-Bench Pro, 93.2 on AIME 2026, 87 on HMMT February 2026, and 72.4 on SWE-Bench Multilingual. All figures come from the release page — no independent audit exists yet at open-weights launch.
How do you run Ling-3.0-flash locally?: Ling-3.0-flash runs on SGLang or a custom vLLM fork published by inclusionAI. Recommended sampling is temperature 0.6, top_p 0.95, top_k 20. The full BF16 checkpoint is 255GB; an FP8 variant at 128GB is also on Hugging Face for smaller GPU setups.
Was Ling-3.0-flash available before the open-weights release?: Yes, but only through hosted APIs. From July 23 to August 3, 2026 Ling-3.0-flash was free on OpenRouter, Vercel AI Gateway and Kilo. Ant Group open-sourced the weights on August 5 under an MIT license, so anyone can now self-host or fine-tune.

Try it

huggingface.co/inclusionAI/Ling-3.0-flash (SGLang or the inclusionAI vLLM fork; temperature 0.6, top_p 0.95)