Perplexity's local-only agent runtime lands on Linux and 24GB RTX cards
- Source
- x.com
- Date
Portable Computer is now available on Linux for @NVIDIA RTX GPUs with 24GB of VRAM or higher. https://t.co/ZhmnPISFEk
Get started with Portable Computer: https://t.co/lzj03mkzXG
Context
Perplexity announced Portable Computer support for Linux machines with NVIDIA RTX GPUs carrying at least 24 GB of video memory on September 3. The earlier DGX Spark launch post described a fully local version of Perplexity Computer in which the orchestrator model, model and all run on the user's hardware. The Linux announcement extends that product to qualifying RTX systems; the current documentation lists one local model, PPLX 27B, for them.
Local execution should not be read as a permanent ban on external services. The current product documentation also says the orchestrator asks for approval before routing a task to a cloud model, separating where the core runtime operates from where an individual task may obtain help.
- multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
- agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Checking sign-in…
Loading comments…