Parallax

build your own ai cluster. run open models across your machines.

[Parallax @tryParallax]

🫡

[Jensen Huang @JensenHuang]

For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.

AI will transform every industry, power every company, and be built by every country.

Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.

The world needs both frontier closed models and frontier open models.

https://t.co/AUKzoQ5Ikb

[Shariq @shariq_ai]

It’s becoming ridiculously easy to run your own AI lab.

With @tryParallax, you can run frontier models locally, keep your data private, and build without depending on the cloud.

The future of AI feels a lot more personal.

[rw ./ @gradientintern]

you can also run the latest and best models of GLM 5.2 on Parallax 👀

run locally with both macs and gpus together or solo with @tryParallax

[MiniMax (official) @MiniMax_AI]

This is a glimpse of where local AI is heading and we are glad to be part of it.

Really impressive work by all the teams involved @Gradient_HQ, @tryParallax, and @GA_agent_ai

[Parallax @tryParallax]

our goal stays the same:

turn the machines on your desk into one local serving layer for powerful open models.

in this demo, we run @MiniMax_AI M3 across local Macs and powers @GA_agent_ai through localhost.

no hosted endpoint. no remote API. everything on device.

[Gradient @Gradient_HQ]

A self-evolving agent + a 428B model + 3 Macs = ?

Your own AI lab.

We ran @MiniMax_AI M3 locally with @tryParallax, right on our desk.

Then @GA_agent_ai took over to create a 5-stock portfolio and write it to disk.

No cloud. No API bills. Nothing left the machine.

Wild to see a ~3K-line agent drive all this with a 400B+ model on local hardware.

Thanks to the GenericAgent and MiniMax teams for making local AI feel real.

[Parallax @tryParallax]

nvidia going all in on local ai.

here's our take: it shouldn't depend on which chip you bought.

sparks, macs, the 5090 already on your desk, we cluster across all of it and split your favorite model pipeline-parallel so it runs fully private and local.

[NVIDIA @nvidia]

NVIDIA RTX Spark: a 1-petaflop superchip, the full CUDA and RTX ecosystem, and Windows-native agents. A new beginning for personal computers.

[Parallax @tryParallax]

mine looks better

[Yuan ./ @yuangao]

Thrilled to see @tryParallax live in production on @Theta_Network.

This is exactly why @Gradient_HQ built Parallax: turning the world’s GPU mesh into a sovereign, distributed token factory.

Congrats on the milestone! 🫡

[Parallax @tryParallax]

glad we could help!

with the agentic adoption soaring, privacy and token cost are already the top concerns for both agent and human users.

that's what parallax's built for.

[Theta Network @Theta_Network]

To make this work, we adapted Parallax, @Gradient_HQ's distributed inference framework, to run across EdgeCloud's global node network. One API endpoint, model split across many machines, no centralized cluster required.

[Parallax @tryParallax]

@Theta_Network @Gradient_HQ 🫡

[Parallax @tryParallax]

@VitalikButerin buy a GPU, get together a group of friends. don’t carry the world on your own shoulders.
we’ve been building this for a while. try parallax for local ai.

[Parallax @tryParallax]

@RoundtableSpace 35b model on a macbook with compressed cache is a solid result.

local inference keeps getting more accessible and it's fun to watch people push the limits of what consumer hardware can do!

[Parallax @tryParallax]

@adrgrondin @PrismML 1-bit model running at 40 tok/s on an iphone.

mlx is making on-device inference surprisingly usable now.

[Parallax @tryParallax]

@ollama local llm + mlx is a great combo! apple silicon keeps getting better for local inference and it's nice to see more players in the ecosystem lean into it properly.

[Parallax @tryParallax]

@tom_doerr single binary, self-hosted, no dependencies.

this is the way local ai should ship. less config, more building.

[Parallax @tryParallax]

@karaage0703 9bから27bへのローカル性能の差がすごい。qwen3.5は今セルフホストするなら最高のモデルの一つ。特に異なるデバイス間でシャーディングするなら。

[Parallax @tryParallax]

TurboQuant tackles one bottleneck: KV cache memory. there's another one that matters just as much in distributed setups: communication latency between nodes.

we built Decentralized Speculative Decoding (DSD) to turn that idle network wait time into useful computation, 2.56x speedup on HumanEval, no retraining needed.

combine cache compression with latency compression and local inference starts looking very different. https://t.co/AF0wpqXIhd

[Parallax @tryParallax]

hf-mount solves the storage side: any model, mounted locally like a drive. the next piece is actually running those models across whatever hardware you have.

that's what parallax does: schedule inference across a pool of heterogeneous GPUs so the model doesn't just live on your machine, it runs there too. mount + serve, fully local.

[Parallax @tryParallax]

@oprydai you don't need to go into debt though. a couple of mac minis or an nvidia card can already run serious models locally. parallax lets you connect whatever hardware you have into one cluster. start small, add devices as you go. the whole point is using what's already on your desk.