NVIDIA RTX Spark laptop runs local agent workload 2x faster than MacBook Pro M5 Pro
ArtificialAnlys · x · 2026-10-16
Artificial Analysis published first AA-AgentPerf-Local results: an NVIDIA RTX Spark N1X laptop (essentially DGX Spark's GB10 — 20-core Arm CPU, 6,144-core Blackwell GPU, up to 128GB unified memory at 300GB/s) completes an 8-task, 168-turn agent workload on Qwen3.8 27B in 18.7 minutes — near DGX Spark (17.3), 2.0x faster than MacBook Pro M5 Pro 64GB (37.6) and 1.8x faster than AMD Ryzen AI Halo (34.5). GeForce RTX 5090 desktop leads at 4.9 minutes. Tested on a prototype 15-inch Surface Laptop Ultra (128GB, $5,900) using NVIDIA's llama.cpp recipes.
Related event: RTX Spark N1X doubles MacBook Pro in first local agent benchmark(4 posts)→
More from Infra
- Phison CEO calls CXMT memory scare a 'ghost story', warns of materials shortage — BenBajarin · 2026-10-16
- Ben Bajarin: The Future of Compute Is Fungible as Hyperscalers Design for Workload Flexibility — BenBajarin · 2026-10-16
- AirLLM runs frontier-size models layer-by-layer: 671B on 12GB VRAM — Aiden_Tech_Ai · 2026-10-16
- NVIDIA Launches cuPotential in CUDA-X to Bring AI Agents to Semiconductor Materials Simulation — tomaszbednarz · 2026-10-16
- Q4-quantized coder model on 8-core CPU builds interactive solar system demo in one shot — IntrepidMindExplorer · 2026-10-16
- TokenSpeed MLA 2 ships for Vera Rubin: up to 3.44× faster Kimi K3 decode — zhyncs42 · 2026-10-16