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.
LatestKRAFTON1-nano
KRAFTONText / LLM

KRAFTON Releases Raon-1-nano, a Sub-1B Open Model

The PUBG studio enters the open-weights race with a compact, Apache 2.0-licensed language model built for lightweight deployment.

Oct 29, 2026
UpdateApache 2.0
Raon-1-nano

KRAFTON, the South Korean game studio best known for PUBG, has quietly stepped into the open model space with Raon-1-nano, a compact text-generation model now available on Hugging Face. The "nano" label signals its focus: a sub-1B parameter footprint aimed at running where larger models can't.

The release ships under the Apache 2.0 license, one of the most permissive options for open weights. That matters for developers who want to fine-tune, embed, or commercialize a model without restrictive usage clauses — a deliberate contrast to the custom licenses attached to many recent releases.

Why it matters

Small models are having a moment. As teams look to put language capabilities on-device, in game clients, or at the edge, a well-built sub-1B model can be more practical than a frontier system that needs a datacenter. For KRAFTON, a company that runs games at massive scale, a lightweight in-house model is a natural fit.

  • Size: under 1 billion parameters, built for efficiency
  • License: Apache 2.0, suitable for commercial use
  • Modality: text generation

As an initial release, Raon-1-nano is light on published specifications — context length and exact parameter counts aren't detailed in the record. Still, its arrival is notable as a sign that game companies, not just AI labs, are beginning to publish their own open weights. More technical details can be found on the model's Hugging Face page.

Sources

  • KRAFTON/Raon-1-nano

    Hugging Face

    Visit
OlderMistral Large 4 Arrives as a 1T-Parameter MoEMistral AI · Text / LLM · 3 weeks agoNewerTencent releases Hunyuan Hy4, an MoE vision-language modelTencent · Text / LLM · 3 weeks ago

Get the model

Hugging Face

Specs

Context window262K tokens
Size7.1 GB
PrecisionBF16
ArchitectureRaon1NanoForCausalLM
LicenseAPACHE-2.0
Downloads2.8K
Likes222

Can you run it?

Runs on just about anything.

  • BF16 (as published)

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

    8.3 GB
  • 8-bit

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

    5 GB
  • 4-bit

    Any modern laptop · 8 GB RAM

    3.3 GB
Your machine
GGUF builds
  • 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 KRAFTON

All KRAFTON releases →
Raon-1-mini (preview)
KRAFTON/Text / LLMConsumer GPU

KRAFTON releases Raon-1-mini preview under Apache 2.0

The Korean game studio behind PUBG puts out a compact, permissively licensed language model as an early preview.

Oct 21, 2026
A.X-K2 Raon Speech 21B-A3B
KRAFTON/Any-to-AnyRuns on a laptop

KRAFTON releases A.X-K2 Raon speech MoE model

The game maker's new open model blends text-to-speech and speech recognition in a single 21B mixture-of-experts system with just 3B active parameters.

Jul 27, 2026
Raon-OpenTTS-1B
KRAFTON/Text → SpeechRuns anywhere

KRAFTON releases 1B zero-shot voice-cloning TTS

Raon-OpenTTS-1B is a flow-matching diffusion transformer that clones English voices from short reference clips.

May 21, 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