gabriel

kernel lover and local ai

[gabriel @gabrielsmAI]

ODS
I'm very happy to be part of this, thank you to everyone who helped contribute and reach 4k stars in such a short time. We’re pressing ahead to ensure everyone has access to high-quality local AI.

[Ahmad @TheAhmadOsman]

Just a reminder that I said this almost a year ago, and now we have something amazing, free, and made by the people for the people at @OsmanticAI

If I say it’ll be done, you can mark me on it

Opensource AI will win and Local AI will be the default.

[Ahmad @TheAhmadOsman]

There’s a difference between having a Kofi link to support your Opensource contributions and begging btw

We even have an Opensource Contributors program at @OsmanticAI where we spend thousands of dollars a month to support our Opensource Contributors ❤️

[gabriel @gabrielsmAI]

@OsmanticAI 🔥🔥

[Osmantic @OsmanticAI]

v3.0 👀👀👀

[Ahmad @TheAhmadOsman]

Open systems always end up winning because openness is freedom and we all are meant to be free

Opensource AI Must Win

[Ahmad @TheAhmadOsman]

If your grandma cannot run Local AI on her laptop from 2013 we'll have failed our mission

That's the bar we're setting for ODS

We're gonna make Local AI the default, and while doing that the word "local" will stop being necessary to begin with (because it's already the default)

[Ahmad @TheAhmadOsman]

@Jason @SecScottBessent This is the timeline Opensource AI wins btw :)

https://t.co/p6lIVhcWHw

[gabriel @gabrielsmAI]

@LLMJunky 🔥🔥

[Mike Bradley @MikeBradleyAI]

Elon quoting Ahmad is the timeline where open source wins BTW 💪❤️

[Ahmad @TheAhmadOsman]

Just a reminder that GLM 5.3 Flash, DeepSeek V4.1 Flash, Qwen 3.8 Next Flash, and even Qwen 3.8 27B are all outperforming (in both intelligence and capabilities) every model that was considered "frontier intelligence" in Xmas 2025 (just 10 months ago)

Opensource AI is on fire

[Mike Bradley @MikeBradleyAI]

Fun video talking about local AI motherboards, what to think about when selecting them for local AI server builds, PCIe lanes, and why all of this stuff matters when you are doing multi GPU work without NVLink. Featuring the ASUS WRX90E-SAGE SE motherboard.

[Ahmad @TheAhmadOsman]

Based on my experience with DeepSeek V4.1 Flash, GLM 5.3, and Kimi K3

- DeepSeek is excellency itself when it comes to pre-training

- Zhipu and Moonshot are better at post-training though

We're so lucky to have such amazing opensource players btw

[Ahmad @TheAhmadOsman]

Playing with a few RTX PRO 6000s and a DGX Station tonight

I feel privileged and that is actually a problem

In a few years, I genuinely believe we won't need such massive amounts of compute to run quality models --- this is the problem we are building @OsmanticAI to fix

[Ahmad @TheAhmadOsman]

Opensource AI must win.

Local AI will be the default.

Freedom of intelligence is a must.

[gabriel @gabrielsmAI]

@TheAhmadOsman legend!!!!

[Ahmad @TheAhmadOsman]

234 days later, we got Opus 4.5 / 4.6 intelligence and capabilities running on a single RTX 3060 with 8GB VRAM

[Ahmad @TheAhmadOsman]

9x size reduction from Qwen 3.8 27B while maintaining 98% of the performance

The future of Local AI is so good you won’t believe it

[PrismML @PrismML]

Today, we’re announcing Ternary Bonsai 2 27B.

Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance.

Two months after the first Bonsai 27B release, the biggest change is quality. The footprint remains 5.9 GB, but the gap to full precision has narrowed materially, with particularly strong gains in agentic coding, multimodal reasoning, and long-horizon tool use.

Ternary Bonsai 2 27B is available today under Apache 2.0.

[NVIDIA RTX Spark @NVIDIARTXSpark]

.@TheAhmadOsman stopped by @MTSlive with a NVIDIA DGX Station (@Dell Pro Max with GB300). 🔥

Thousands of tokens per second all running locally.

[Ahmad @TheAhmadOsman]

Prediction

We will have a Kimi K3 / Fable 5 equivalent intelligence running on a single RTX 5090 in less than 18 months from now