Portable Computer Now Runs AI Agents and Models Locally on NVIDIA RTX PCs

Melvin Vivas · X video post · 2026-09-15 · 0:32 · 561 views · Open on X

Topics: AI Agents, Tool Use & MCP, AI Dev Tools & Productivity · Level: beginner

Summary

Melvin Vivas reacts to an announcement, asking whether it will run on his RTX 3090. The quoted announcement says Portable Computer is now available on Windows PCs with NVIDIA RTX GPUs. It runs the agent harness, the agents and the models locally, and can call frontier cloud models when needed. The item doesn't explain how it works. The transcript is unusable: it's one stray machine-generated line.

Key points

• Portable Computer is now available on Windows PCs with NVIDIA RTX GPUs.
• It runs the agent harness, the agents and the models locally on your own PC.
• It works with local files and connected apps without sending tasks to the cloud, which helps with privacy.
• It's hybrid: you can still use frontier cloud models when you need them.
• The creator asks whether a consumer RTX 3090 (24 GB of VRAM) is enough. The post doesn't answer, so check the official hardware requirements.
• The spoken transcript has nothing useful in it. All the information comes from the post text.

Resources mentioned

• Portable Computer · tool · perplexity.ai · paid
  A desktop agent app that runs the agent harness, agents and models locally on Windows PCs with NVIDIA RTX GPUs, and can also use frontier cloud models.
• NVIDIA GeForce RTX 3090 · tool · nvidia.com · paid
  Consumer GPU with 24 GB of VRAM, used here to run a long-context LLM locally.
  Also in: Long-Context Local LLM on an RTX 3090: .env Config and ~64 tok/s Benchmark (Melvin Vivas on X · notes), Running Ornith-1.5-35B-A3B (Q4_K_M) at 128k Context on an RTX 3090 with llama.cpp (Melvin Vivas on X · notes), Generating AI Video Locally with MiniMax H3 in ComfyUI on an RTX 3090 (Melvin Vivas on X · notes), Running MiniMax H3 Locally on a Single RTX 3090 (Demo) (Melvin Vivas on X · notes) and 2 more

Try this

• Look up Portable Computer's hardware requirements to see whether your RTX GPU (for example, an RTX 3090) is supported.