Aetherix Technical White Papers

In-depth technical analysis of AI inference on NVIDIA hardware. From Jetson-based edge AI to DGX Spark clusters and RTX PRO workstations — deployment guides, cluster setups and measured LLM and computer-vision benchmarks.

Trusted Jetson Hardware Provider for Edge AI · Netherlands-based · European shipping

Latest White Papers

Technical GuideConditional Memory and Offloading in LLM Inference

How model architecture decides what must remain in GPU memory and what can move to host RAM or NVMe: conditional memory, memory hierarchies of DGX Spark, RTX PRO 6000 and DGX B300, and measured results with DeepSeek-V4.1-Flash and Qwen3.8-Flash-Next.

September 2026
LLM DeploymentDeepSeek-V4.1-Flash 8× DGX Spark TP8 Deployment

Deployment of DeepSeek-V4.1-Flash (763B MoE, FP8, DSpark k=5) on 8× NVIDIA DGX Spark (GB10) with TP8: two configurations (300K Engram-in-memory, 1M Engram-on-disk), NCCL optimization, benchmark results and TP4 comparison.

September 2026
CV BenchmarkCV Inference Benchmark Explorer

Explore computer-vision inference benchmarks on NVIDIA GPUs and Jetson devices. Pick a GPU and a detection model to see the frame rate it sustains, how it falls as cameras are added, and how many cameras it carries at your target FPS.

September 2026
LLM DeploymentDeepSeek-V4.1-Flash 4× DGX Spark Deployment

Deployment of DeepSeek-V4.1-Flash (763B MoE, FP8, DSpark k=5) on 4× NVIDIA DGX Spark (GB10) with tensor parallelism: vLLM build chain, 7 SM 12.1a patches, Engram-on-disk, benchmark results and B300 comparison.

September 2026
LLM BenchmarkLLM Inference Benchmark Explorer

Explore LLM inference benchmarks on NVIDIA DGX Spark, DGX B300, RTX PRO 6000 Blackwell and Jetson Thor. Filter by model, parameter count, device, quantization and concurrency, and set your own performance targets.

August 2026
Architecture ComparisonNVIDIA DGX B300 vs GB300 NVL72 Cluster Architecture Comparison

Technical comparison of two NVIDIA Blackwell Ultra architectures, DGX B300 and GB300 NVL72: system design, scaling approach, network fabric, power and cooling, and which workloads suit which platform.

August 2026
LLM BenchmarkKimi K3 Inference Benchmark on DGX-B300

Performance evaluation of Moonshot AI Kimi K3 (2.8T MoE, MXFP4) on NVIDIA DGX-B300 (8x Blackwell Ultra, TP=8): vLLM vs SGLang, direct vs DSpark speculative decoding, with SLO-driven capacity planning.

July 2026
Cluster SetupDGX Spark 3-Node AI Cluster Setup Guide

Ring (mesh) topology AI cluster setup with 3 NVIDIA DGX Spark nodes: management and compute networks, RoCEv2/RDMA, sparkrun configuration.

July 2026
Cluster SetupDGX Spark 2-Node AI Cluster Setup Guide

Point-to-point topology AI cluster setup with 2 NVIDIA DGX Spark nodes: management and compute networks, RoCEv2/RDMA, sparkrun configuration.

July 2026
Cluster SetupDGX Spark 8-Node AI Cluster Setup Guide

Switch-based AI cluster setup with 8 NVIDIA DGX Spark nodes over a MikroTik CRS804 with 200G breakout: management and compute networks, RoCEv2/RDMA, sparkrun and NAS.

July 2026
Cluster SetupDGX Spark 4-Node AI Cluster Setup Guide

Switch-based AI cluster setup with 4 NVIDIA DGX Spark nodes over a MikroTik CRS812: management and compute networks, RoCEv2/RDMA, sparkrun and NAS.

July 2026
LLM ScalingQwen3.6-27B DGX Spark Cluster Scaling

Multi-node scaling study of Qwen3.6-27B-NVFP4 on 1x, 2x, and 4x NVIDIA DGX Spark (GB10): tensor parallelism over 200GbE, SLO-driven capacity planning, and TP-vs-replication deployment guidance.

July 2026
LLM BenchmarkQwen3.6-27B DGX Spark Benchmark

Performance evaluation of the Qwen3.6-27B model on the NVIDIA DGX Spark (GB10) platform with FP8, FP8-MTP, AWQ-MTP, NVFP4, and NVFP4-MTP quantization variants.

July 2026
Decision GuideLocal LLM Usage Guide

End-to-end decision guide for local LLM usage: hardware (NVIDIA Jetson, RTX PRO, DGX Spark, DGX/HGX), model selection, software stack and scenario mapping.

June 2026

Areas of Expertise

Embedded & Edge AI

Real-time inference, robotics and automation on the NVIDIA Jetson family — developer kits, AI kits and carrier boards.

Mini Supercomputer

NVIDIA DGX Spark with the GB10 architecture — compact, powerful and scalable personal AI systems, single or clustered.

Professional GPU

AI and rendering workloads on NVIDIA RTX PRO Blackwell graphics cards.