The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • Hardware estimates
  • RSS feed
  • llms.txt
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestinclusionAI3.0-tiny
inclusionAIText / LLM

inclusionAI Releases Ling-3.0-tiny, an MIT-Licensed MoE

The new hybrid mixture-of-experts model targets efficient text generation under a permissive license.

Aug 10, 2026
NotableMIT
Ling-3.0-tiny

inclusionAI has published Ling-3.0-tiny, a compact language model built on a hybrid mixture-of-experts (MoE) architecture. The model is available now on Hugging Face and is distributed under the MIT license, one of the most permissive terms in open-source software.

The "tiny" label positions this release as the entry point in the Ling 3.0 family, aimed at developers who want a lighter footprint without abandoning the efficiency gains that MoE designs promise. Mixture-of-experts models activate only a subset of their parameters for any given token, which can deliver strong quality per unit of compute compared with dense models of similar size.

Why it matters

Permissive licensing remains a decisive factor for teams choosing which open models to build on. MIT terms allow commercial use, modification, and redistribution with minimal restrictions, lowering the barrier for startups and researchers who want to fine-tune or embed the model in their own products.

  • Hybrid MoE architecture for efficient inference
  • MIT license, suitable for commercial deployment
  • Text generation as the primary modality

The release record does not specify parameter counts, context length, or benchmark results, so builders will want to consult the model card directly before committing to production use. As the first public entry in the Ling 3.0 line, it also signals where inclusionAI intends to take the family next.

Sources

  • inclusionAI/Ling-3.0-tiny

    Hugging Face

    Visit
OlderMeta's Muse Glimmer 30B Targets Local Agentic CodingMeta AI · Vision-Language · 3 months agoNewerBilibili's IndexTTS-2.5 Refines Zero-Shot Voice CloningIndexTeam · Text → Speech · 3 months ago

Get the model

Hugging Face

Specs

Context window131K tokens
Size15.8 GB
PrecisionBF16
ArchitectureBailingMoeV3ForCausalLM
LicenseMIT
Downloads13.3K
Likes592

Can you run it?

Runs on a laptop — about 6 GB at 4-bit.

  • BF16 (as published)

    24 GB GPU (RTX 3090 / 4090) · 32 GB Mac

    17 GB
  • 8-bit

    12 GB GPU (RTX 3060 / 4070) · 16 GB Mac

    9.6 GB
  • 4-bit

    8 GB GPU (RTX 4060) · 16 GB laptop or Mac

    6 GB
Your machine
GGUF builds
  • Mixture-of-experts: every expert must be loaded, so memory follows total parameters, not the active slice.
  • KV cache sized for 8,192 tokens of context; longer prompts need proportionally more.

Based on Hugging Face weights metadata. Assumes an 8K context and ~1 GB runtime overhead; actual needs vary. How we estimate


Modalities

Text / LLM

The Weekly Weights

Every open release that mattered, one email a week.

0 comments

No comments yet. Be the first to weigh in.

More from inclusionAI

All inclusionAI releases →
Ling-3.1-flash-1019
inclusionAI/Text / LLMDatacenter

inclusionAI releases Ling-3.1-flash, an MIT MoE model

The new text model pairs a hybrid mixture-of-experts design with FP8 weights under a permissive license.

Oct 27, 2026
Ling-3.1-flash
inclusionAI/Text / LLMDatacenter

inclusionAI releases Ling-3.1-flash under MIT license

A new hybrid mixture-of-experts text model arrives on Hugging Face with permissive licensing and a focus on fast inference.

Oct 13, 2026
Ming-Image-0.1-Design
inclusionAI/Text → ImageRuns on a laptop

inclusionAI's Ming-Image targets graphic design

A new MIT-licensed text-to-image model leans into legible text rendering and transparent RGBA output for design work.

Sep 17, 2026

More in Text / LLM

All Text / LLM →
Aion-1.0-Instruct-2.3B
Microsoft/Text / LLMRuns anywhere

Microsoft's Aion 1.0 Instruct is a compact 2.3B chat model

A small, multilingual instruction-tuned model aimed at chat and summarization lands on Hugging Face.

Nov 18, 2026
SenseNova-Loop-9B
SenseTime/Vision-LanguageRuns on a laptop

SenseTime Releases Looped 9B Multimodal Model

The company's new SenseNova-Loop-9B pairs vision-language capabilities with a recurrent looped-transformer design.

Nov 17, 2026
Hunyuan Hy4-flash
Tencent/Vision-LanguageMulti-GPU server

Tencent releases Hunyuan Hy4-flash multimodal MoE

The lightweight, mixture-of-experts model adds vision and text instruction-following to Tencent's open Hunyuan lineup.

Nov 17, 2026