Sunday, 8 Nov 2026
Subscribe to AIWatcher
AIWatcher
  • Home
  • News

    Google takes over a troubled Wyoming campus and tees up 17 billion

    By
    AIWadmin

    Eight hundred hacking agents sat open and nobody noticed

    By
    AIWadmin

    An unreleased Claude build closed a proof that stumped theorists since 2008

    By
    AIWadmin

    Agility Robotics reaches Nasdaq without a shipping product

    By
    AIWadmin

    Claude now reads your statements and keeps its hands off the money

    By
    AIWadmin

    Google stretches Gemini video to 15 seconds and cuts the rate

    By
    AIWadmin
  • Articles

    Meta lets Muse agents build their own little rooms

    By
    AIWadmin

    Physicl raises 10 million to make simulation honest enough for robots

    By
    AIWadmin

    Texans turned the data center boom into a ballot question

    By
    AIWadmin

    Clutch sits at 50 times revenue in a reported Palo Alto deal

    By
    AIWadmin

    Ramp’s card data says the AI spending boom has plateaued

    By
    AIWadmin

    Inkling 2 Small jumps to 31 on intelligence index for Thinking Machines

    By
    AIWadmin
  • Spotlight

    Underdog shrinks a voice engine to 32MB inside a browser game

    By
    AIWadmin

    Together lets coding agents rewrite the forward pass all day

    By
    AIWadmin

    Half a million H200 chips wait out a decision in Hong Kong

    By
    AIWadmin

    OpenAI’s bug hunt turns up 948 paths to root

    By
    AIWadmin

    Baidu hands out a 280B model with no instructions attached

    By
    AIWadmin

    Claude cites a wire service after a quiet licensing turn

    By
    AIWadmin
  • About
    • Mission
    • Services
    • Contact
  • Newsletter
  • Shop
    • All Items
    • By Category
      • Hats
      • T-Shirts
    • Cart
  • 🔥
  • Alignment
  • Classification
  • Distillation
  • Explainability
  • Hallucination
  • Legal/Compliance
  • Medical
  • NLM
  • Mobility
  • Research
  • Robotics
  • Safety
  • Startups
  • Prompt
  • Python
  • RAG
  • RLHF
  • Token
  • Vision
Font ResizerAa
AIWatcherAIWatcher
  • Home
  • News
  • Articles
  • Spotlight
  • About
  • Newsletter
  • Shop
Search
  • Home
  • News
  • Articles
  • Spotlight
  • About
    • Mission
    • Services
    • Contact
  • Newsletter
  • Shop
    • All Items
    • By Category
    • Cart
Have an existing account? Sign In
Follow US
© 2022 Foxiz News Network. Ruby Design Company. All Rights Reserved.
News

Perplexity packs its agent computer into a DGX Spark

A local-first build of the agentic platform runs models on-device with zero per-token cost.

AIWadmin
Last updated: August 26, 2026 8:32 pm
AIWadmin
ByAIWadmin
Global AI news & information.
Follow:
Share
SHARE

Perplexity has taken its agentic Computer platform fully local with a release called Portable Computer. Everything ships as one system: the agent harness, the orchestrator, the planner, the tool router, and the post-trained models all run on the device. The target box is an NVIDIA DGX Spark, and local steps carry no per-token charge.

Two models ship at launch: Qwen 3.8 27B and PPLX 27B, Perplexity’s own post-trained variant, with NVIDIA Nemotron 3.5 Lightning expected later. The whole setup sits behind an OS-level sandbox. Processes, filesystem paths, and network access are all confined to it. If the sandbox cannot start, tool execution is disabled rather than downgraded.

The setup is local-first but not local-only. When a step requires live web data or frontier reasoning, the orchestrator pauses and asks for approval, running a PII classifier over the context and showing users exactly what would leave the machine. Escalated steps go to one of 15+ cloud models, which receive only text guidance and no direct access to local files or tools.

Benchmarks on Perplexity’s own 53-task work bench put the Qwen-powered build at 82.6% and the PPLX variant at 85.4%. Terminal Bench 2.1 results tell a hybrid story: a fully local run scored 59.6% at near-zero marginal cost, escalation lifted that to 73% at about $0.415 per rollout, and Claude Opus 5 alone hit 82.4% at roughly $0.65.

Linux users on Pro, Max, and Enterprise plans get access first, with Windows support in September. The hardware bar is a GB10-class machine or an RTX GPU with 24GB of VRAM.

TAGGED:AI AgentsDGX SparkEdge ComputingLocal AINvidiaPerplexity
SOURCES:MarkTechPost
Share This Article
Email Copy Link Print
ByAIWadmin
Follow:
Global AI news & information.
Previous Article Meta’s MetaRoCE lets AI Ethernet survive packet loss
Next Article McKinsey finds AI profits still flat as spending climbs

You Might Also Like

News

Four Gemini agents finish Minecraft with no humans involved

By
AIWadmin
News

Claude Code bills for blank thinking blocks users never see

By
AIWadmin
News

Amodei takes the AI slowdown argument to the White House table

By
AIWadmin
News

OpenAI lines up a $30B bridge at a $1.25T valuation

By
AIWadmin
AIWatcher
Facebook Twitter Youtube Linkedin Rss

Global AI News and Information
AIWatcher is your definitive source for AI updates worldwide, from Silicon Valley to Shanghai. Our industry coverage keeps you in the loop with the latest news and trends shaping the future of AI.

Quick Links
  • News
  • Articles
  • Spotlight
  • ICYMI
About Us
  • Mission
  • Services
  • Contact
  • Privacy Policy
  • Legal
© 2026 AIWatcher. All Rights Reserved.