Offline Base

Making Local AI easy for all.

[Offline Base @offlinebase]

Hey,

We started Offline Base because:

1. We believe Local[ly runnable], Open Source, and Small Language Models are good enough to do just about everything that people use frontier models for.

2. We believe that running models locally is the solution to the many problems associated with or attributed to data centers and cloud based models

3. We believe that teaching everyone about data privacy is a lost cause (sort of)

4. We want to ensure that no one gets left behind in this new AI-Native World

5. We believe that Open Source models are more than good enough.

We hope to make Local AI easy for all.

[Offline Base @offlinebase]

Despite the name, at Offline base, we’re interested in both running models locally and running open source models through awesome cloud providers.

We’ve silently been running an experiment - https://t.co/KEXAUR1Gay where anyone can use any open source model for free, with no logins, and zero data retention.

We kept hearing that people knew of open source models but never really tried them.

Curiosities are beginning to shift from ‘how do I use an open source model’ to ‘how do I use CoreWeave, Baseten, Modal, and other neoclouds’. Of course folks are curious; Neoclouds have raised 10+ billion dollars in the past year alone.

With that being said, we’ve spun out https://t.co/uoxSaqYnuy, https://t.co/pSvZ0EiUbX, and https://t.co/HGIBOnRCJl

Everyone should be able to learn from, benefit from, and contribute to the future of AI.

@modal @CoreWeave @baseten @wandb

[Offline Base @offlinebase]

Awesome. Working on this, but for ppl that don't use 5k dollar laptops.

[Perplexity @perplexity_ai]

Introducing hybrid compute in Perplexity Computer.

Computer can start a task in the cloud, then move to a local model that runs on your Mac. Use it for steps involving private files or sensitive data.

Available today in the Perplexity Mac app.

[Offline Base @offlinebase]

@PeasantSmith @NVIDIARobotics We have a few. If there are any experiments you want to run, let us know. We can run it for you and give you credit!

[Offline Base @offlinebase]

@NVIDIARobotics This is what I am working on!

[Offline Base @offlinebase]

more here https://t.co/a6tE6nAoKo

[Offline Base @offlinebase]

Hey,

We started Offline Base because:

1. We believe Local[ly runnable], Open Source, and Small Language Models are good enough to do just about everything that people use frontier models for.

2. We believe that running models locally is the solution to the many problems associated with or attributed to data centers and cloud based models

3. We believe that teaching everyone about data privacy is a lost cause (sort of)

4. We want to ensure that no one gets left behind in this new AI-Native World

5. We believe that Open Source models are more than good enough.

We hope to make Local AI easy for all.

[Offline Base @offlinebase]

@ZixuanLi_ @opencode @OpenRouter Try it for free with no login here https://t.co/4ixBCY5uBU

[Offline Base @offlinebase]

@DesignArena @Zai_org Try it for free with no login here https://t.co/4ixBCY5uBU

[Offline Base @offlinebase]

@opencode Try it for free with no login here https://t.co/4ixBCY5uBU

[Offline Base @offlinebase]

@arena @Zai_org Try it for free with no login here https://t.co/4ixBCY5uBU

[Offline Base @offlinebase]

@Zai_org Try it for free with no login here https://t.co/4ixBCY5uBU

[Offline Base @offlinebase]

@ArtificialAnlys @Zai_org Try it for free with no login here https://t.co/4ixBCY5uBU

[Offline Base @offlinebase]

@NVIDIAAI @nvidia Introducing NVIDIA Jetson Orin Nano 2 👏 Built to bring frontier intelligence to entry-level edge AI, this robotics computer will deliver: • 2x the inference performance of Jetson Orin Nano Super • 40% lower power consumption at the same performance in 15W mode • The same compact form factor Read the press release 📷 https://t.co/dsHfaJ84Mj

[Offline Base @offlinebase]

Some awesome new updates in the local AI space:
- @perplexity_ai is going local with Perplexity Computer
- @IBM just released Granite 4.2
- @Apple 's releasing the new mac mini with their m6 chip
- @nvidia is releasing the jetson orin nano 2

Thread below with more

[Offline Base @offlinebase]

@Apple is releasing their new mac mini and mac studio in late September: https://t.co/hFDgG3P4Yi

[Tim Cook @tim_cook]

The new Mac mini is here. Small in size. Big on performance. From everyday productivity to all things AI, it can help you do it all.

[Offline Base @offlinebase]

@ArtificialAnlys This is awesome! We are working to build devices and systems to enable people to swich to using these models.

[Offline Base @offlinebase]

@shuai_bai_ Try it here https://t.co/4ixBCY5uBU

[Offline Base @offlinebase]

@ryan_marten If you want to try glm 5.3 for free -> https://t.co/NYbFqesvfI