Nvidia · Chips and hardware · Pricing and access
Nvidia unveils a 64 GB DGX Spark that runs models of up to 100 billion parameters locally
Nvidia announced a new 64 GB configuration of DGX Spark on October 2, a year after the desktop AI computer first went on sale with 128 GB of memory. The new version keeps the same GB10 Grace Blackwell chip and software stack and will be sold only through Acer, ASUS, Dell, Gigabyte, HP and MSI from October 23, starting at $4,999. Nvidia says a single unit can run models of up to 100 billion parameters fully on device, while two units linked by a cable pool 128 GB and support up to 200 billion. Amid rising memory prices, the 128 GB model has climbed from its $3,999 launch price to $6,950.
Sources
- Nvidia, “NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI”, (blogs.nvidia.com)
- Nvidia, “NVIDIA DGX Spark Arrives for World’s AI Developers”, (investor.nvidia.com)
- ServeTheHome, “NVIDIA DGX Spark 64GB Launched and Big 128GB GB10 Price Increases”, (servethehome.com)
- Hardware Busters, “Nvidia DGX Spark 64GB Arrives at $4,999 as the 128GB Model Jumps to $6,950”, (hwbusters.com)
About this story
This story was posted on Instagram by @jarrus.tech on Oct. 10, 2026.
Spotted an error in this story? [email protected] · Instagram
Short link: thejarrus.com/en/dgx-spark
This story in Turkish: Nvidia, 100 milyar parametreye kadar modelleri yerel çalıştıran DGX Spark’ın 64 GB’lık sürümünü tanıttı
On the same topic
Higgsfield launches Ads Studio, turning a website into ad images for about 20 cents each
Higgsfield’s Ads Studio, announced October 1, builds a brand kit from a website and makes up to 20 static ads per product at about $0.20 each.
Microsoft releases three new voice models, one transcribing 60 languages in real time
On October 1, Microsoft AI announced MAI-Transcribe-2-Streaming, which transcribes 60 languages in real time, and the 23-language MAI-Voice-2.1 and Flash.
Anthropic releases Claude Haiku 5.5 at 90% lower prices
Claude Haiku 5.5, released Oct. 7, costs 90% less than Haiku 4.5 for prompts up to 100,000 tokens. It leads on benchmarks but uses more tokens per task.