Perplexity Portable Computer lands on Windows RTX PCs with 24GB+ VRAM
nvidia · x · 2026-09-14
Perplexity's local agent platform, Portable Computer, is now available on Windows for GeForce RTX and RTX PRO GPUs with 24GB+ VRAM, extending earlier support for DGX Spark and Linux RTX machines.
- Plans and executes multistep tasks locally: analyzing data, combining information across files, handling recurring work
- Sensitive data stays on device; local work doesn't consume Perplexity Computer credits
- Includes a built-in browser and SPACE sandbox; can escalate to cloud models with user permission for harder reasoning
- Ships with a local model (e.g., Qwen 3.8 27B) post-trained for Perplexity Computer and optimized for RTX GPUs
More from Infra
- NVIDIA: full-stack NIM tuning delivers 2.5x more concurrent users on Nemotron 3 Ultra — NVIDIAAI · 2026-09-15
- How Much Does Local LLM Inference Really Cost? A Dev Added an Electricity Calculator — giveen · 2026-09-15
- Hugging Face Rounds Up Which Open LLMs Are Best for On-Device Inference — NielsRogge · 2026-09-15
- Single Pure-C99 Inference Engine Runs Both BitNet Ternary and GGUF, No Python or CUDA — shifu_legend · 2026-09-15
- Dev weighs ChatGPT subscription via OAuth vs API pricing for a production RAG app — builtforoutput · 2026-09-15
- Cognichip launches ACI Enterprise: one engineer finishes chip front-end design in 10 days — kimmonismus · 2026-09-15