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.
LatestMicrosoft1.0 Instruct
MicrosoftText / LLM

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
NotableOther
Aion-1.0-Instruct-2.3B

Microsoft has published Aion-1.0-Instruct-2.3B, a compact instruction-tuned language model built for conversational tasks and summarization across multiple languages. At 2.3 billion parameters, it sits firmly in the small-model tier that has become increasingly popular for teams that need capable text generation without the cost and latency of frontier-scale systems.

The model is a dense (non-mixture-of-experts) text LLM, released under a custom license noted on the model card. Microsoft frames Aion 1.0 Instruct around multilingual chat and summarization, two workloads where small models have matured quickly over the past year.

Why it matters

Small, instruction-tuned models have become the practical backbone of many real-world deployments, where predictable cost and on-device or edge-friendly footprints matter more than leaderboard supremacy. A 2.3B model is small enough to run on modest hardware yet large enough to handle everyday assistant tasks.

  • Roughly 2.3B parameters, dense architecture
  • Tuned for multilingual chat and summarization
  • Distributed via Hugging Face under a custom license

As an initial release, Aion 1.0 Instruct establishes a new model family rather than iterating on an existing one. Developers evaluating it should check the model card for license terms, supported languages, and usage details before building on top of it.

Sources

  • microsoft/Aion-1.0-Instruct-2.3B

    Hugging Face

    Visit
OlderReson8's Rumble-2-Flash Puts ASR in 0.5B ParamsReson8 · Speech → Text · 3 days ago

Get the model

Hugging Face

Specs

Parameters2.3B
Context window33K tokens
Size4.6 GB
PrecisionBF16
ArchitectureAionInstructForCausalLM
LicenseOTHER
Downloads1.6K
Likes92

Can you run it?

Runs on just about anything.

  • BF16 (as published)

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

    6.5 GB
  • 8-bit

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

    4.4 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 Microsoft

All Microsoft releases →
Mage-VL-Cowork
Microsoft/Vision-LanguageRuns on a laptop

Microsoft's Mage-VL-Cowork takes on computer-use tasks

A new vision-language agent model aims to operate GUIs, write code, and work the terminal.

Oct 30, 2026
FrogNano-4B
Microsoft/Text / LLMRuns on a laptop

Microsoft Releases FrogNano-4B Under MIT License

The compact 4-billion-parameter text model lands on Hugging Face with a permissive license aimed at developers.

Sep 17, 2026
VibeVoice-ASR-Streaming-7B
Microsoft/Speech → TextRuns on a laptop

Microsoft's VibeVoice ASR brings streaming speech-to-text

A 7-billion-parameter model targets real-time, multilingual transcription with an open release on Hugging Face.

Sep 2, 2026

More in Text / LLM

All Text / LLM →
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
Sage S2.1 Flash
Internlm/ReasoningMulti-GPU server

InternLM's Sage S2.1 Flash targets scientific reasoning

The 320B mixture-of-experts model is built to reason over scientific evidence and act inside interactive environments.

Nov 15, 2026