Skip to content
Cut to the source.The real-time AI news wire.
Saved in a cookie.

Search tips

  • "exact phrase" the words together, in this order
  • -word leave out stories with the word
  • topic:robotics a topic by ID or name; quote names with spaces: topic:"open-weight models"
  • category:"AI agents" a category
  • company:openai a company, person, product or organization (also entity:)
  • source:forbes.com a publisher by site or name
  • type:analysis news, analysis, opinion, research paper and other kinds
  • after:2026-11-01 stories on or after that New York day; before:2026-11-10 on or before it
Subscribe
NewsletterAboutModels & ResearchAI AgentsAI DevelopmentInfrastructure & HardwareImage, Video & AudioRobotics & Autonomous SystemsBusiness & IndustryPolicy & RegulationSafety & SecurityBenchmarks & EvaluationOpen Source & CommunityAI in Society
Models & ResearchAI AgentsAI DevelopmentInfrastructure & HardwareImage, Video & AudioRobotics & Autonomous SystemsBusiness & IndustryPolicy & RegulationSafety & SecurityBenchmarks & EvaluationOpen Source & CommunityAI in Society
Robotics & Autonomous SystemsBusiness & IndustryPolicy & RegulationSafety & SecurityBenchmarks & EvaluationOpen Source & CommunityAI in Society

19 NovInfrastructure & Hardwareshattered.io

Ryzen AI Halo vs DGX Spark: 192 GB vs 128 GB [2026]

Four gold compact DGX Spark mini computers stacked and linked by braided cables on a wooden desk beside a mug and a green pen

AIAI-generated summary AMD says its Ryzen AI Halo tops out at 192 GB of unified memory while Nvidia limits its DGX Spark to 128 GB, with both running at the same memory bandwidth. AMD says the PRO 495 version of Ryzen AI Halo can run models of 300 billion parameters and larger at 4-bit quantization, whereas Nvidia rates its 128 GB box for models up to roughly 200 billion parameters.

NVIDIA AI Chips GPUs Quantization Local AI

Earlier:
192GB Local AI: Halo, Spark, Multi-GPU vs Mac
+1 more earlier storiesCollapse earlier stories
  • 192GB Local AI: Halo, Spark, Multi-GPU vs Mac
  • Apple’s $2,899 MacBook PROLED hides a massive unified memory bottleneck — why I think power users should abandon macOS for Nvidia RTX Spark and AMD Strix Halo
Read at shattered.io

Share onXLinkedInBlueskyEmail

Latest stories

  • Europe needs ‘innovation-friendly’ regulation to catch up on AI, German official says

    19 November 2026

    Semafor — Marco-Alexander Breit said Europe needs to adjust its regulatory policy to halt a brain drain.

  • Copilot Home and Office go generally available with editing and coauthoring

    19 November 2026

    aipingnews.com — Copilot Home and Office integration became generally available on November 17.

  • Go from customer questions to completed transactions

    19 November 2026

    elevenlabs.io — Learn how to build an AI agent to handle customer booking conversations from start to finish with ElevenAgents

  • PixlStash 2.0: Image Library and LoRA Training in One Application

    19 November 2026

    mlllm.io — PixlStash 2.0 (v2.0.0 released November 10, 2026, v2.0.1 released November 16) is an open-source desktop application that groups faces by similarity...

  • Nvidia's October quarter revenues hit $115.8B, up 103%, with data center revenue up 110%

    19 November 2026

    gamesbeat.com — Nvidia reported revenues of $115.8 billion for the third fiscal quarter ended October 25, up 103% from a year ago.

TruncatedTruncated

Continuous coverage across AI research, agentic systems, infrastructure, and regulation.

Content

  • Latest
  • Archive
  • Topics
  • Newsletter
  • RSS Feed

About

  • About
  • Developers
  • Publishers
  • Advertise

Legal

  • Impressum
  • Privacy Policy
  • Terms & Conditions
  • Disclaimer
  • Contact

© 2026 Truncated. All rights reserved.

Truncated™ is a trademark of Three Things Media.