NVIDIA Brings Nemotron to RTX Spark, Announces DeepSeek V4 Flash Running in 60GB
ryanshrout · x · 2026-10-08
At a Microsoft Windows AI event, Ryan Shrout revealed NVIDIA is bringing a new Nemotron model to RTX Spark for hybrid local+cloud inference, and announced a DeepSeek V4 Flash variant running in just 60GB of memory. HydraFusion will route coding tasks to local compute as part of the "hybrid intelligence" vision.
Related event: Microsoft and Nvidia Unite to Reshape the PC with Hybrid AI and RTX Spark(13 posts)→
More from Infra
- Microsoft launches Surface Spark with Nvidia: $6k for 128GB, odd form factor — casper_hansen_ · 2026-10-08
- Google launches first test satellite carrying 4 TPUs for its space-based ML infrastructure moonshot — CurieuxExplorer · 2026-10-08
- GPU rental platform Lium hits all-time-high utilization, courts idle GPU owners with 95%+ revenue share — const_reborn · 2026-10-08
- Marvell details Google chip deal worth up to $120B as inference accelerators split from TPUs — demian_ai · 2026-10-08
- llama.cpp Takes the Stage at Microsoft's Windows Event, Creator Celebrates Local AI Milestone — ggerganov · 2026-10-08
- Tracking a 24/7 agent for 30 days: $6 VPS, $22 API, and uptime is the real leak — YamOk7317 · 2026-10-08