hatem rabeh (@rabehhatem) 's Twitter Profile
hatem rabeh

@rabehhatem

ID: 365430005

calendar_today31-08-2011 12:38:42

59 Tweet

43 Followers

356 Following

Linus Ekenstam – eu/acc (@linusekenstam) 's Twitter Profile Photo

OpenSource voice model taking on the giants 🤯 Chatterbox Turbo beats ElevenLabs Turbo & Cartesia Sonic 3 in independent reviews, that’s unbelievable. - 5 second voice cloning - <150ms time-to-first-sound - Paralinguistic tags

Md Ismail Šojal 🕷️ (@0x0sojalsec) 's Twitter Profile Photo

Run 70B LLMs on a 4GB GPU with layer-wise inference and memory optimization, quantization optional🫣 - arxiv.org/abs/2212.09720 - github.com/0xSojalSec/air… #Ai #infosec #AIAgent

Run 70B LLMs on a 4GB GPU with layer-wise inference and memory optimization, quantization optional🫣

- arxiv.org/abs/2212.09720
- github.com/0xSojalSec/air…

#Ai #infosec #AIAgent
TuringPost (@theturingpost) 's Twitter Profile Photo

A useful repo on how to build a production-ready agentic AI system You have to watch two things all the time: • Agent behavior → reasoning, tool use, memory, safety • System reliability and performance→ latency, uptime, cost, recovery under load This repo explains how to

A useful repo on how to build a production-ready agentic AI system

You have to watch two things all the time:
• Agent behavior → reasoning, tool use, memory, safety
• System reliability and performance→ latency, uptime, cost, recovery under load

This repo explains how to
Leonardo Grigorio (@leonardogrig) 's Twitter Profile Photo

Just open-sourced a Claude Skills Generator using Firecrawl /agent Any docs URL → complete skill Decision trees, workflows, error recovery, full folder structure.

Lior⚡ (@lioronai) 's Twitter Profile Photo

You can now run 70B LLMs on a 4GB GPU. AirLLM just made massive models usable on low-memory hardware. 𝗪𝗵𝗮𝘁 𝗷𝘂𝘀𝘁 𝗵𝗮𝗽𝗽𝗲𝗻𝗲𝗱 AirLLM released memory-optimized inference for large language models. It runs 70B models on 4GB VRAM. It can even run 405B Llama 3.1 on 8GB

You can now run 70B LLMs on a 4GB GPU.

AirLLM just made massive models usable on low-memory hardware.

𝗪𝗵𝗮𝘁 𝗷𝘂𝘀𝘁 𝗵𝗮𝗽𝗽𝗲𝗻𝗲𝗱
AirLLM released memory-optimized inference for large language models.

It runs 70B models on 4GB VRAM.
It can even run 405B Llama 3.1 on 8GB
Oliver Prompts (@oliviscusai) 's Twitter Profile Photo

Microsoft killed the GPU mafia 🤯 They finally open-sourced their 1-bit LLM inference framework called bitnet.cpp. It lets you run 100B parameter models on your local CPU without GPUs. - 6.17x faster inference - 82.2% less energy on CPUs 100% Open Source.

Anil Chandra Naidu Matcha (@matchaman11) 's Twitter Profile Photo

Day 3 of open-sourcing a real alternative to Higgsfield AI 🚀 Introducing Cinema Studio 🎬 Now with: Camera , Lens , Aperture , Focal length control ✅ Free ✅ BYOK ✅ Open-source Say goodbye to Higgsfield subscriptions. Link to the project in comments 👇

Mark Gadala-Maria (@markgadala) 's Twitter Profile Photo

🚨This is incredible. Someone open sourced a full company using AI agents. Anyone can now run an agency instantly using AI. Repo: github.com/msitarzewski/a…

🚨This is incredible.

Someone open sourced a full company using AI agents.

Anyone can now run an agency instantly using AI.

Repo: github.com/msitarzewski/a…