ASUS Ascent GX10 Desktop AI Supercomputer (NVIDIA GB10 128GB)
Compact desktop AI supercomputer built on the NVIDIA GB10 Grace Blackwell Superchip (20-core Arm CPU + Blackwell GPU via 900 GB/s NVLink-C2C), delivering 1,000 FP4 TOPS (1 PFLOP) with 128GB unified LPDDR5X and dual 200GbE ConnectX-7 clustering.
Editorial Rating Methodology (★ 4.9 / 5.0): This score is an internal editorial evaluation compiled by the RECIWO Labs editorial team—not a user poll or crowd-voted rating. It assesses published silicon compute efficiency (25%), optical/sensor/actuator engineering (25%), battery & thermal envelope (20%), SDK/software openness (15%), and price-to-specification value (15%) based on official manufacturer datasheets and public technical documentation. Learn more about our evaluation rubric →
Key Engineering Highlights
- Co-engineered with NVIDIA around the GB10 Grace Blackwell Superchip connected via 900 GB/s NVLink-C2C, delivering up to 1 PetaFLOP (1,000 TOPS) of sparse FP4 Tensor performance
- Integrated NVIDIA ConnectX-7 SmartNIC (dual 200GbE QSFP) lets developers link two Ascent GX10 units with a single DAC cable to form a 256GB unified-memory node capable of running Llama-3.1-405B locally
- Pre-installed NVIDIA DGX OS (Ubuntu Linux) ships with full CUDA, TensorRT-LLM, NVIDIA NIM microservices, and PyTorch out of the box
Full Hardware Specifications
| Processor / Edge SoC | NVIDIA GB10 Grace Blackwell Superchip (20-Core Arm v9.2 CPU + 5th-Gen Tensor Blackwell GPU) |
|---|---|
| AI Model Stack | Up to 200B Parameter Local LLMs (Single Node) or 405B Parameter Models (2-Node ConnectX-7 Cluster) |
| Display & Optics | HDMI 2.1b + 4× USB-C (USB 3.2 Gen 2x2 w/ DisplayPort Alt-Mode & 180W USB-PD Power) |
| Camera & Vision | None (Palm-Sized 1.2L Desktop & Edge Lab AI Supercomputer Form Factor) |
| Measured Weight | 1.25kg (150 × 150 × 51mm Custom ASUS Dual-Fan Vapor-Chamber CNC Enclosure) |
| Battery & Runtime | 180W–240W USB-C PD External Power Adapter (~140W Peak GB10 Superchip Envelope) |
| Connectivity & I/O | Dual 200GbE NVIDIA ConnectX-7 QSFP Ports + 10GbE RJ-45 + Wi-Fi 7 + Bluetooth 5.4 |
| Sensors & Acoustics | 128GB 256-Bit LPDDR5X-8533 Coherent Memory (~273 GB/s) + Up to 4TB PCIe Gen5 NVMe SSD |
⚖️ Side-by-Side Comparison: ASUS Ascent GX10 Desktop AI Supercomputer (NVIDIA GB10 128GB) vs. Edge Compute & DevKits Peers
Direct specification comparison against leading competing devices in the Edge Compute & DevKits category.
| Specification | ASUS Ascent GX10 Desktop AI Supercomputer (NVIDIA GB10 128GB) (Current) | NVIDIA Jetson Orin NX Super Edge AI DevKit → | Xiaozhi AI Voice Cube Pro (ESP32-S3 Open DevKit) → | Apple Mac mini (M5 Pro 64GB) Private AI Node → |
|---|---|---|---|---|
| Brand | ASUS × NVIDIA | NVIDIA | Open Hardware Community | Apple |
| Retail Price | $3,499 | $499 | $12 | $1,799 |
| Editorial Rating | ||||
| Edge SoC | NVIDIA GB10 Grace Blackwell Superchip (20-Core Arm v9.2 CPU + 5th-Gen Tensor Blackwell GPU) | NVIDIA Ampere GPU (1024 CUDA + 32 Tensor Cores) | Espressif ESP32-S3R8 (Dual-Core LX7 @ 240MHz + 8MB PSRAM) | Apple M5 Pro (14c CPU + 20c GPU + 16c Neural Engine) |
| AI Model Stack | Up to 200B Parameter Local LLMs (Single Node) or 405B Parameter Models (2-Node ConnectX-7 Cluster) | Runs Llama-3.2 8B / Qwen2.5-VL 7B / YOLO11 Locally | Edge ESP-SR Wake + Realtime Cloud Voice LLMs | MLX Accelerated Qwen3-32B / Llama-3.3-70B |
| Display / Optics | HDMI 2.1b + 4× USB-C (USB 3.2 Gen 2x2 w/ DisplayPort Alt-Mode & 180W USB-PD Power) | HDMI 2.1 / DP 1.4 (Up to 8K) | 1.28-inch Circular IPS LCD (240×240) / 0.96" OLED | Supports up to three 6K displays |
| Camera | None (Palm-Sized 1.2L Desktop & Edge Lab AI Supercomputer Form Factor) | Dual MIPI CSI-2 Camera Lanes + 4× USB 3.2 | Optional OV2640 / GC2145 Camera Module | External USB-C / Studio Display Camera |
| Weight | 1.25kg (150 × 150 × 51mm Custom ASUS Dual-Fan Vapor-Chamber CNC Enclosure) | 450g (including active heatsink & carrier board) | 62g (with 3D-printed enclosure & speaker cavity) | 730g |
| Battery | 180W–240W USB-C PD External Power Adapter (~140W Peak GB10 Superchip Envelope) | 19V DC Input (15W–40W configurable TDP) | 800mAh LiPo (5h continuous dialogue) | Internal 155W PSU (4W idle draw) |
📚 Related Engineering Teardowns & Reviews
Browse All 113 Articles →HP Z2 Mini G1a (Strix Halo 128GB) vs ASUS Ascent GX10 (GB10) vs NVIDIA DGX Spark Comparison: 96GB UMA VRAM vs 1-PFLOP FP4
A technical architecture and specification comparison of the HP Z2 Mini G1a ($2,299, 2.9L AMD Ryzen AI Max+ PRO 395 workstation with 128GB LPDDR5X-8533 and 96GB allocatable UMA VRAM), ASUS Ascent GX10 ($3,499, NVIDIA GB10 Grace Blackwell Superchip with 1,000 FP4 TOPS, 128GB unified RAM, and 200GbE ConnectX-7), Framework Desktop ($1,999), and NVIDIA DGX Spark ($3,999).
Astribot S1 vs MagicLab MagicBot Gen1 vs Galbot G1 Comparison: 10 m/s Cable-Driven VLA Arms vs 20kg Factory Bimanual Humanoid
A technical specification and actuation comparison of the Astribot S1 ($69,000, 170cm omnidirectional wheeled bimanual robot with ≥10 m/s cable-driven end-effector velocity, 100 m/s² acceleration, ±0.1mm repeatability, and 5kg/arm full-reach payload), MagicLab MagicBot Gen1 ($42,000, 42-DoF bipedal industrial humanoid with 350 N·m actuators and 20kg dual-arm payload), and Galbot G1 ($38,000).
Captify Pro vs Chamelo Music Shield vs Vuzix Z100 Comparison: 37g Binocular Live-Captioning HUD vs 0.1s Electrochromic Audio Glasses
A technical specification and optical architecture comparison of the Captify Pro ($699, 37g binocular 1,500-nit MicroLED waveguide smart glasses with acoustic beamforming for deaf/hard-of-hearing live captioning and 40+ language translation), Chamelo Music Shield ($249, 38g 0.1-second Eclipse liquid-crystal electrochromic tint-shifting AI audio sports glasses), and Vuzix Z100 ($499).
BOOX Note Max (13.3\" Carta 1300) vs Supernote Manta (A5X2) vs Viwoods AiPaper Mini Comparison: A4 BSR FPGA vs Modular Ceramic-Nib E-Ink
A technical specification and display architecture comparison of the Onyx BOOX Note Max ($649, 13.3-inch 300 PPI Carta 1300 A4 E-Ink tablet in a 4.6mm chassis with 2.8GHz octa-core CPU, BSR FPGA refresh co-processor, 6GB+128GB, and Smart Scribe AI), Supernote Manta A5X2 ($459, 10.7-inch 300 PPI flexible Carta 1300 notebook with FeelWrite 2 soft film, wear-free ceramic stylus, and modular replaceable battery/motherboard), and Viwoods AiPaper Mini ($429).
