Skip to main content
← Back to news

Ling 3.1 Flash: 560B MoE with 25B active, 1M-token context and MIT license

Model releases
Source:Hugging Face
inclusionAI releases Ling 3.1 Flash: 560B total parameters, 25B active per Token, hybrid MoE architecture, up to a 1M-Token Context Window and an MIT license. At 4 bits it fits in 512GB of Unified memory — the edge case of today's Mac Studio M5 Ultra article.
Read original article

Related articles

Ling 3.1 Flash: 560B open-weight with MIT license and 1M context — what changes if you have 24GB of VRAM

Ling 3.1 Flash ships 560B open-weight parameters under an MIT license with 1M context. It won't fit in 24GB of VRAM, but the quantizations, 25B active MoE and the real numbers change the calculation.

Mac Studio M5 Ultra: 512GB of unified memory on the desktop

Four dies, 512GB of unified memory at 1.2 TB/s: the Mac Studio M5 Ultra runs 100-560B MoE models locally. The speed math, the cost comparison with the DGX Station, and when the Mac is the right choice.

Mac Studio M5 Ultra: practical 512GB guide - models that fit and GGUF setup

The 512GB Mac Studio holds a 560B MoE at 4 bit with a large context. This guide covers the 4-bit rule, GGUF setup in three paths, the real bottleneck (the KV cache), and the Mac-vs-API cost comparison with the numbers on the table.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

🌏

inclusionAI Ling 3.1 Flash (MoE)

Models

Modello MoE open-weight di inclusionAI: 560B parametri totali, 25B attivi per token, architettura ibrida (attenzione lineare KDA + Gated MLA), finestra di contesto fino a 1M di token, licenza MIT. Reasoning ibrido con modalità di pensiero on/off. A 4 bit entra in 512GB di memoria unificata.

⚡

DeepSeek V4.1 Flash

Models

DeepSeek's MoE model with 552B total parameters and 8-16B active per token. 1M-token context, MIT license: free commercial use. Built for online serving, too large for local use on a single PC.

🐑

Llama 4 Maverick (MoE)

Models

Il modello MoE grande della famiglia Llama 4 di Meta: 400B di parametri totali con 17B attivi (128 esperti). Contesto 1M di token, nativamente multimodale (testo+immagini), licenza comunitaria Meta. Richiede multi-GPU o macchine con memoria unificata 128GB+ anche quantizzato.

🐑

Llama 4 Scout (MoE)

Models

The compact MoE of the Llama 4 family: 17B active parameters out of 109B total (16 experts). Meta's community license allows free use under 700 million monthly users. One of the best entry points into the Llama 4 family.

Browse all resources