EVAL Engine

$EVAL Building & / Powered by @Chromia & @virtuals_io

[EVAL Engine @Eval_Engine]

Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android

Zero servers
Zero cloud
Zero deployment

The whole model lives on your phone

[EVAL Engine @Eval_Engine]

Unbound+ is here, now on iPhone.

The model already runs fully on your phone.

→ Web search for live answers
→ Vision to read your images
→ No cloud, API and runs fully on-device

No subscription.

Free chat stays free.

Join the beta: https://t.co/6rnA56g6wa

[Yosef Soso @0x50so]

It’s no longer Spray and Pray, now for most agent users it’s either Pray that agents wont spray or use Atbash

[ATBASH @ATBASHai]

This is only a tip of the iceberg, AI Agents can just access things and no your memory file cannot stop them.

Action Boundary Control is the only solution.

https://t.co/Nbw57m3dh8

[Chromia | Power to the Public @Chromia]

Chromia currently operate two AI products in production.

Unbound: the model with no guardrails that runs on-device - directly from your browser.
https://t.co/tgfmJG8uAM

https://t.co/fClCbZToty: the governance layer that intercepts irreversible agent actions and secures every verdict on-chain.
https://t.co/OAWMs4ln1d

Yet the market categorizes Chromia alongside AI L1s trading at massive multiples.

NEAR operates at nearly 100x the market cap.

Same sector.

A different volume of functional software.

[or perelman @perelmanor]

Cooking

[Chromia | Power to the Public @Chromia]

Chromia is a full relational Layer-1 chain; yet it trades at $20M.

ICP: $1.5B.
Filecoin: $900M.
The Graph: $280M.
Arweave: $154M.

Chromia brings agent queries native to the chain, something none of its peers offer.

As AI agents move on-chain, the infrastructure they run on matters more.

[EVAL Engine @Eval_Engine]

"A red fox curled beneath paper lanterns, ink wash style, gentle shadows"

Generated in the browser.

No API
No subscription
No token limit

Model cached locally, runs on WebGPU.

Go wild here - https://t.co/BKnJrom6Zn

[EVAL Engine @Eval_Engine]

Added an uncensored text to image model from @PrismML to Unbound

Fully on-device.

No server round-trip, no content moderation pipeline, no logs sitting on someone else's GPU.

Just you, the model, and whatever you want to make.

↓

[superoo7 @superoo7]

The rest of the wave worth watching:

$POD @dphnAI (launched on @AskVenice)
$SUPERGEMMA @0xSUPERGEMMA from @jangqai (launched on @bankrbot)
$EVAL from @Eval_Engine & @Chromia (launched on @virtuals_io)

All open-weight, all on @Base 👀

[superoo7 @superoo7]

This is happening faster than I expected: @dealignai $DEAL just launched, newest of the "uncensored-model-token wave"

Open weights → real HF downloads → token on @base

$POD $DEAL $SUPERGEMMA $EVAL

[EVAL Engine @Eval_Engine]

Let’s go

@XiaomiMiMo 🤝 @Eval_Engine

[superoo7 @superoo7]

Thanks @XiaomiMiMo for supporting @Eval_Engine, we got 200M tokens to spend for improving it 🔥

[superoo7 @superoo7]

Thanks @XiaomiMiMo for supporting @Eval_Engine, we got 200M tokens to spend for improving it 🔥

[EVAL Engine @Eval_Engine]

96hrs since Unbound went live on @Eval_Engine

Total of 6k downloads across various Unbound models running fully offline

No servers, no cloud subscription

Chat with Unbound - https://t.co/ZZpVkOwoh7

chromaway:native $EVAL

[EVAL Engine @Eval_Engine]

Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android

Zero servers
Zero cloud
Zero deployment

The whole model lives on your phone

[superoo7 @superoo7]

@huggingface @base @dphnAI @0xSUPERGEMMA @Eval_Engine @jun_song Unbound from Eval Engine
https://t.co/FDCRevErU5

[superoo7 @superoo7]

More and more open-weight uncensored models on @Huggingface are launching tokens on @Base 👀

@dphnAI $POD — Dolphin series
@0xSUPERGEMMA $SUPERGEMMA — SuperGemma (Gemma fine-tune)
@eval_engine $EVAL — Unbound model

[Chromia | Power to the Public @Chromia]

Your AI Agent reads a tool description, and that description quietly rewrites its instructions.

No alert. No crash.

It just starts working for someone else.

That is the part nobody is watching.

With Atbash. every AI Agent action gets a verdict before it runs:

pass

hold

block

Your agent secured with https://t.co/fClCbZToty

[EVAL Engine @Eval_Engine]

WebGPU support enables our Unbound model to run entirely on the browser

Try Unbound here - https://t.co/wuOYatFYrT

[Reese Levine @reeselevine]

WebGPU support in llama.cpp is here! Check out our blog post introducing it: https://t.co/3OUusMYqIY

Run local models in your browser, with GPU acceleration. No data leaves your computer!

Thanks to everyone who's made this possible, especially @ggerganov

[EVAL Engine @Eval_Engine]

Update for those hitting out of memory errors (OOM)

WebGPU can be slow (the browser caps how much GPU or system memory a tab can use) so for faster performance it's better to run it through @ollama

Download here - https://t.co/Deu5vtUyQY

[EVAL Engine @Eval_Engine]

Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android

Zero servers
Zero cloud
Zero deployment

The whole model lives on your phone

[EVAL Engine @Eval_Engine]

Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android

Zero servers
Zero cloud
Zero deployment

The whole model lives on your phone

[Yeou Jie @YeouJie]

We just released a new AI model that can run on any device, making it more accessible to you guys 👍🏻

https://t.co/GXzCdwPI5E