Perplexity brings fully local AI workflows to Macs with 36GB+ RAM
AravSrinivas · x · 2026-10-21
Following September's Hybrid Compute, Perplexity now lets users run its entire Computer experience—including the harness and orchestrator—locally on a Mac.
- Requirement: an Apple Silicon Mac with at least 36GB of RAM
- Model choices: Qwen 3.6 or PPLX Pro, a Perplexity post-trained variant of Qwen 3.6 fine-tuned for Computer use
- Pitch: privacy (email data stays on-device) and credit savings; users can still authorize a frontier cloud model to pitch in when needed
- The company argues that as local machines handle more demanding workflows, they'll take a larger share of users' AI workloads
Related event: Perplexity Computer Now Runs Fully On-Device on Mac(4 posts)→
More from Infra
- Pichai: everyone is massively short on AI compute — 'everyone wishes you had two times what you had planned' — firstadopter · 2026-10-21
- Stanford CS336 Lecture 6: fused Triton kernels cut softmax memory traffic ~4x — stanfordnlp · 2026-10-21
- General Compute partners with Positron AI: Atlas memory-centric hardware ships Q1 2027 — aftahi_ai · 2026-10-21
- AI bond issuance hits $419B in 2026, up 90% from all of 2025 — SumitGup · 2026-10-21
- AI Obsession Is Making Enterprises Neglect Cloud FinOps, Expert Warns — DavidLinthicum · 2026-10-21
- DeepSeek bottleneck is compute, not demand: 1GW cluster could train a far stronger model, says leak account — teortaxesTex · 2026-10-21