Arnav

get your training up, not your explaining up
linkedin scares me

[Arnav @_dostmalone]

Introducing Bloc: A package manager and runtime orchestrator for reproducible local AI. Share optimized model recipes and run them anywhere with a single command :

bloc deploy arnav080/step-3-7-flash-nvfp4

free and open-s.
https://t.co/OzVezE6E5y

[Arnav @_dostmalone]

the ui is super smooth and amazing [idk why the videos lagging a bit / jitters] go try it out for yourselves it free!!

https://t.co/RKRpO5w910

[the only reason im running a 0.5 model is bec im broke and thats all my m1 macbook can run (only got 6ish gb of ram free]

[Bloc @runbloc]

Bloc Studio in action!

[Arnav @_dostmalone]

ever seen such an active dev who listens to the community? (i am the community i alone am the community)

[Arnav @_dostmalone]

does anyone know a good way to render pixel-art characters like this directly inside a terminal app?

[Arnav @_dostmalone]

ngl, that looks pretty slick (by that i mean resembles claude code)

[Bloc @runbloc]

we now have Bloc Studio - a terminal workspace for interacting with your Bloc-hosted models.

Built-in UI for Llama.cpp, vLLM and SGLang engines.
try it now: https://t.co/cAVmaQHWd8

[Arnav @_dostmalone]

@runbloc way to goo gang (ik i made this im js commenting for reach)

[Bloc @runbloc]

We're building the Docker for Local AI.

A simple way to package and share complete AI environments including models, runtimes, dependencies, and configuration.

One command. Same setup. Run anywhere.
Free and Open-source

we’re live on Product Hunt today.

[Arnav @_dostmalone]

@heyclicky spoken like a true gentleman

[Arnav @_dostmalone]

@0xSero ui too clean, gotta get something like this into bloc

[Arnav @_dostmalone]

this might be the best tweet ive read in a while

[dax @thdxr]

someone made a fork of opencode that routes through the unsecured ai endpoints from chipotle

[Arnav @_dostmalone]

@NewsWire_US

[Bloc @runbloc]

v0.4.0 is live with SGLang support! Will fix the bugs and then start implementing the support for ik_llama.cpp

[Arnav @_dostmalone]

@0xSero Hey OxSero, amazing work!! i turned the config into a bloc recipe so people can reproduce the setup with a single command.

(building this open-source package manager and runtime) would love to hear your thoughts!

https://t.co/GceD6hkcVJ

[Arnav @_dostmalone]

i strongly believe people dont understand how big local ai is going to be in the near future esp for businesses. imagine having to not pay per token, no sending sensitive data to third parties, predictable costs

just owning the models, owning the infrastructure owning the data

[Arnav @_dostmalone]

@Hikari_07_jp when do you think we'll start seeing meaningful enterprise adoption of local/open-source LLM's?

[Bloc @runbloc]

Docker made servers reproducible.
We're trying to do the same for local AI.

Today:
"Use this model."
"Use these launch flags."
"Install these dependencies."

With Bloc:
bloc run arnav080/step-3-7-flash-nvfp4

website: https://t.co/fpNcAEW6X7
repo: https://t.co/S5TUuqYCnt

[Arnav @_dostmalone]

@JoelDeTeves https://t.co/Z5YOBU4jPC

[Arnav @_dostmalone]

@JoelDeTeves Hey Joel, I turned this config text into ready-to-run Bloc recipes so people can reproduce the setups with a single command [building bloc an open-s local model package manager and registry] would love to hear your thoughts!

bloc deploy arnav080/ornstein3.6-27b-dual-3090-mtp-JDT

[Arnav @_dostmalone]

@Hikari_07_jp Hey Hikari, Amazing stuff! I turned the three configs into ready-to-run Bloc recipes so people can reproduce the setups with a single command instead of copying launch flags from the thread.
https://t.co/43N8I44HE9