Perplexity brings Portable Computer local models to Windows RTX PCs with 24GB+ VRAM
testingcatalog · x · 2026-09-15
Perplexity extends Portable Computer to Windows PCs with NVIDIA RTX GPUs
- Available on RTX GPUs with 24GB+ VRAM, alongside new support for local MCPs and scheduled tasks
- The feature previously shipped only on NVIDIA DGX Spark devices
- Local models include PPLX 27B (Perplexity's post-trained Qwen 3.8 27B); stock Qwen 3.8 27B is unavailable on Windows, and the 30B MoE Nemotron 3.5 Lightning (3B active) is listed as coming soon
More from Infra
- effect-harness on Cloudflare: run agent loops, tools and credentials on separate VMs — samgoodwin89 · 2026-10-31
- Google's Project Suncatcher boots TPU in orbit and beams back first AI response — sundarpichai · 2026-10-31
- Together AI launches Post-Training platform for agentic RL with tool-use environments — togethercompute · 2026-10-31
- General Compute raises $100M for inference capacity as CoreWeave stock hits 12-month low — YvesMulkers · 2026-10-31
- Analyst warns of unstable AI compute feedback loop as Kioxia's NAND price warning triggers flash crash — bookwormengr · 2026-10-31
- SOMA launches enterprise prompt-compression layer claiming 20%+ inference savings — markjeffrey · 2026-10-31