MSI EdgeXpert 4TB AI Supercomputer — NVIDIA DGX Spark Platform
- AI Processor: NVIDIA® GB10 Grace Blackwell Superchip — 1 petaFLOP AI Performance (FP4, Sparse); 5th-Gen Tensor Cores; TF32, FP16, BF16, INT8, FP8, FP6, FP4
- CPU: NVIDIA® Grace CPU — Arm 20-core (10× Cortex-X925 + 10× Cortex-A725)
- Memory: 128 GB LPDDR5x Unified System Memory — 256-bit interface, 273 GB/s bandwidth; run models up to 200B parameters
- Storage: 4 TB NVMe M.2 SSD with self-encryption
- Connectivity: Wi-Fi 7 | Bluetooth® 5.3 | 10 GbE (ConnectX-7 Smart NIC) | 4× USB 3.2 Type-C (20 Gb/s)
- Display Output: 1× HDMI 2.1a + 4× DisplayPort 1.4a via USB-C
- OS: NVIDIA® DGX™ OS — AI software stack pre-installed
- Form Factor: Compact Mini PC — 151 × 151 × 52 mm, 1.19L, 1.2 kg | Cluster 2 units for 405B-parameter models | 3-Year Warranty
Out of stock
Email when stock available
We build the right tech for you
Bangalore's trusted tech store since 2010
- Lifetime in-store technical supportWalk in any time — no AMC, no fees. In-store service only.
- Authorised dealerSealed box, full manufacturer warranty, GST invoice
- Free same-day delivery across Bangalore
- Price matchFind it cheaper at any authorised seller and we'll match it
- No-Cost EMI & Cash on Delivery
- Free laptop bagWith every laptop — no minimum spend
The MSI EdgeXpert (4TB) brings petaFLOP-class AI computing to your desk. Powered by the NVIDIA® GB10 Grace Blackwell Superchip with 128 GB LPDDR5x unified system memory and a 4 TB self-encrypting NVMe M.2 SSD, it delivers 1 petaFLOP AI performance in a compact 1.2-litre form factor. Run large language models up to 200 billion parameters, fine-tune models up to 70 billion parameters, or cluster two EdgeXpert units to tackle models up to 405 billion parameters. Built on the NVIDIA® DGX™ Spark platform, the EdgeXpert ships with the full NVIDIA DGX software stack — ready for AI research, deep learning, data science, and computer vision workflows straight out of the box.
| Product Info | |
| SKU / Part Number | 9S6-C9311-65S |
| EAN / GTIN | 4711377407434 |
| Product Type | Mini AI Supercomputer (Personal AI Cloud) |
| Series | MSI EdgeXpert |
| Platform | NVIDIA® DGX™ Spark Platform |
| Recommended Usage | AI Research · Deep Learning · Data Science · Computer Vision · Large Language Models · Generative AI |
| Colour | Black |
| Form Factor | Mini PC — 1.2-litre compact desktop |
| AI Architecture & GPU | |
| Architecture | NVIDIA® Grace Blackwell |
| GPU | NVIDIA® GB10 Grace Blackwell Superchip |
| AI Tensor Performance | 1 petaFLOP (FP4, Sparse) |
| CUDA Cores | Blackwell Generation |
| Tensor Cores | 5th Generation |
| Tensor Core Data Formats | TF32 · FP16 · BF16 · INT8 · FP8 · FP6 · FP4 |
| RT Cores | 4th Generation |
| Processor (CPU) | |
| Processor | NVIDIA® Grace CPU |
| Architecture | Arm 20-core (10× Cortex-X925 + 10× Cortex-A725) |
| System Memory | |
| System Memory | 128 GB LPDDR5x |
| Memory Type | Unified (CPU–GPU coherent shared memory) |
| Memory Interface | 256-bit |
| Memory Bandwidth | 273 GB/s |
| Available for Workloads | ~100 GB |
| Max Model Size (Single Unit) | Run up to 200B parameters · Fine-tune up to 70B parameters |
| Storage | |
| Storage | 4 TB NVMe M.2 with self-encryption |
| Display Outputs | |
| HDMI | 1× HDMI 2.1a |
| DisplayPort | 4× DP 1.4a (via USB-C) |
| Total Display Outputs | Up to 5 simultaneous displays |
| Connectivity & Communications | |
| USB | 4× USB 3.2 Type-C (up to 20 Gb/s) |
| Ethernet | 1× RJ-45 — 10 GbE |
| Network Adapter | ConnectX-7 Smart NIC |
| Wi-Fi | Wi-Fi 7 |
| Bluetooth | Bluetooth® 5.3 |
| Audio Output | HDMI multichannel audio |
| High-Performance Clustering | |
| Cluster Interface | ConnectX-7 (QSFP — up to 400G) |
| Maximum Cluster Size | 2× MSI EdgeXpert units |
| Clustered Model Support | Up to 405 billion parameters |
| QSFP Cable | Sold separately — MSI P/N: 956-C931-101 |
| Media Engine | |
| NVENC (Video Encoder) | 1× |
| NVDEC (Video Decoder) | 1× |
| Operating System | |
| Pre-Installed OS | NVIDIA® DGX™ OS |
| Software Stack | Full NVIDIA AI software stack included (CUDA, cuDNN, TensorRT, NGC catalogue) |
| Dimensions, Weight & Power | |
| Dimensions (L × W × H) | 151 × 151 × 52 mm (1.19L) |
| Weight | 1.2 kg |
| Power | 280 W (USB-C PSU) |
| Warranty & Services | |
| Warranty | 3-Year Warranty ✅ |
| Country of Origin | |
| Country of Origin | China |
| AI Superchip | NVIDIA GB10 Grace Blackwell |
|---|---|
| AI Performance | 1 PetaFLOP (FP4) |
| Unified Memory | 128 GB LPDDR5x |
| Model Capacity | Up to 200B params |
| AI Storage | 4 TB NVMe |
| AI Networking | 10 GbE, ConnectX-7 200GbE, Wi-Fi 7 |
| AI CPU | 20-core Arm (Grace) |
| AI Operating System | NVIDIA DGX OS |
| AI Form Factor | Mini |
| Color | Black |
Frequently Asked Questions
Can the MSI EdgeXpert handle large language models like Llama 3?
The MSI EdgeXpert supports large language models up to 200 billion parameters because it is engineered for high-end AI workloads. This system features 128 gigabytes of unified LPDDR5x memory and the NVIDIA GB10 Grace Blackwell superchip. These technical specifications make it an ideal choice for local large language model development and fine-tuning. You can utilize this powerful hardware for your AI projects right here in Bangalore.
How much does the MSI EdgeXpert AI Supercomputer cost at YourShoppy?
The MSI EdgeXpert is available for purchase at YourShoppy for the current listed price. We maintain competitive pricing for this high-performance hardware to support your local AI development needs. You should check our current availability status directly on the product page to see if the unit is ready for immediate pickup at our Bangalore store.
Is the MSI EdgeXpert suitable for a home office or small AI startup?
The MSI EdgeXpert is highly suitable for small AI startups because it delivers one PetaFLOP of AI performance in a compact mini form factor. Many of our local Bangalore startup clients prefer this model because it provides enterprise-grade computing power without requiring a dedicated server room. You do not need complex industrial cooling infrastructure to operate this system in your own office space.
What kind of warranty and support does YourShoppy provide for MSI AI systems?
Every MSI EdgeXpert purchased from YourShoppy includes the standard manufacturer warranty to protect your investment. Because this is a specialized AI supercomputer, our team in Bangalore provides dedicated support to ensure your NVIDIA DGX OS environment is correctly configured. We help you set up your research or development projects from day one to ensure you get the most out of your hardware.
Does the MSI EdgeXpert support high-speed networking for data-heavy AI tasks?
The MSI EdgeXpert supports high-speed networking through its ConnectX-7 200GbE interface and Wi-Fi 7 capabilities. These features ensure that your data pipelines remain unthrottled during intensive operations. Whether you are training complex models or processing massive datasets, the 10 GbE and high-speed networking options provide the bandwidth necessary for professional AI workflows.
How does the NVIDIA Grace Blackwell chip in the MSI EdgeXpert compare to standard workstations?
The MSI EdgeXpert outperforms standard workstations by using the NVIDIA GB10 Grace Blackwell superchip with a unified memory architecture. While standard workstations often struggle with memory bottlenecks, this architecture allows the CPU and GPU to share data seamlessly at 273 gigabytes per second bandwidth. This provides a massive performance leap for AI tasks compared to traditional consumer-grade desktop hardware.
Is the MSI EdgeXpert currently in stock at the Bangalore store?
The current availability status for the MSI EdgeXpert at our Bangalore store is listed as available on our website. We maintain regular inventory of this high-demand AI hardware for local research labs and developers. We recommend placing your order online to reserve your unit, as these specialized systems are frequently requested by AI developers across the city.
Related products
Asus Ascent GX10 AI Supercomputer — GB10 Grace Blackwell, 128GB, 1TB (Ubuntu)
- NVIDIA® GB10 Grace Blackwell Superchip — 20-core Armv9.2 CPU + Blackwell GPU | up to 1000 AI TOPS (1 PFLOP FP4)
- 128 GB LPDDR5x Unified Memory (CPU + GPU share one pool — no bandwidth bottleneck)
- 1 TB M.2 NVMe PCIe 4.0 SSD | Ubuntu Linux | NVIDIA DGX Spark platform
- Wi-Fi 7 (802.11be) + Bluetooth 5.4 | 10G Ethernet + NVIDIA ConnectX-7 SmartNIC
- 4× USB-C 3.2 Gen 2×2 (20 Gbps) — 3× with DisplayPort 2.1 | 1× 180W PD-in
- HDMI 2.1 | up to 4 simultaneous displays | 150 × 150 × 51 mm | 1.48 kg
- Run 200B+ parameter AI models locally — scale to 256 GB via NVLink (2× GX10)
- 3-Year Warranty
Asus Ascent GX10 AI Supercomputer — GB10 Grace Blackwell, 128GB, 2TB (Ubuntu)
- NVIDIA® GB10 Grace Blackwell Superchip — 20-core Armv9.2 CPU + Blackwell GPU | up to 1000 AI TOPS (1 PFLOP FP4)
- 128 GB LPDDR5x Unified Memory (CPU + GPU share one pool — no bandwidth bottleneck)
- 2 TB M.2 NVMe PCIe 4.0 SSD | Ubuntu Linux | NVIDIA DGX Spark platform
- Wi-Fi 7 (802.11be) + Bluetooth 5.4 | 10G Ethernet + NVIDIA ConnectX-7 SmartNIC
- 4× USB-C 3.2 Gen 2×2 (20 Gbps) — 3× with DisplayPort 2.1 | 1× 180W PD-in
- HDMI 2.1 | up to 4 simultaneous displays | 150 × 150 × 51 mm | 1.48 kg
- Run 200B+ parameter AI models locally — scale to 256 GB via NVLink (2× GX10)
- 3-Year Warranty
ASUS Ascent GX10 AI Supercomputer NVIDIA® GB10 Grace Blackwell Superchip 128GB LPDDR5x 4TB NVMe PCIe 5.0 SSD Ubuntu
- NVIDIA® GB10 Grace Blackwell Superchip — 20-core Armv9.2 CPU + Blackwell GPU | up to 1000 AI TOPS (1 PFLOP FP4)
- 128 GB LPDDR5x Unified Memory (CPU + GPU share one pool — no bandwidth bottleneck)
- 4 TB M.2 NVMe PCIe 5.0 SSD | Ubuntu Linux | NVIDIA DGX Spark platform
- Wi-Fi 7 (802.11be) + Bluetooth 5.4 | 10G Ethernet + NVIDIA ConnectX-7 SmartNIC
- 4× USB-C 3.2 Gen 2×2 (20 Gbps) — 3× with DisplayPort 2.1 | 1× 180W PD-in
- HDMI 2.1 | up to 4 simultaneous displays | 150 × 150 × 51 mm | 1.48 kg
- Run 200B+ parameter AI models locally — scale to 256 GB via NVLink (2× GX10)
- 3-Year Warranty
Dell Pro Max with GB10 (FCM1253) Micro AI Desktop – NVIDIA GB10 Grace Blackwell / 128GB Unified / 4TB SSD / NVIDIA DGX OS
- NVIDIA GB10 Grace Blackwell Superchip — 20-core Arm CPU, 16 MB L2 Cache
- NVIDIA Blackwell GPU (integrated, unified with GB10) for local AI inferencing & development
- 128 GB LPDDR5x coherent unified system memory (273 GB/s)
- 4 TB M.2 2242 SSD (Self-Encrypting, Opal 2.0)
- NVIDIA DGX™ OS
- ConnectX-7 Smart NIC (2 × 200G QSFP) + 10GbE LAN + Wi-Fi 7 + Bluetooth 5.4
- Compact Micro Form Factor (150 × 150 mm, 1.31 kg) — 280 W USB-C power
- 1-Year Basic Onsite Warranty
NVIDIA DGX Spark 4TB Personal AI Supercomputer
- AI Processor: NVIDIA® GB10 Grace Blackwell Superchip — 1 petaFLOP AI Performance (FP4, Sparse); 5th-Gen Tensor Cores; 4th-Gen RT Cores
- CPU: NVIDIA® Grace CPU — Arm 20-core (10× Cortex-X925 + 10× Cortex-A725)
- Memory: 128 GB LPDDR5x Unified System Memory — 256-bit interface, 273 GB/s bandwidth; run models up to 200B parameters
- Storage: 4 TB NVMe M.2 SSD with self-encryption
- Connectivity: Wi-Fi 7 | Bluetooth® 5.3 | 10 GbE (ConnectX-7 Smart NIC @ 200 Gbps) | 4× USB Type-C
- Display Output: 1× HDMI 2.1a + up to 3× DisplayPort via USB-C
- OS: NVIDIA® DGX™ OS — AI software stack pre-installed
- Form Factor: Compact Mini PC — 150 × 150 × 50.5 mm, ~1.14L, 1.2 kg | Cluster 2 units for 405B-parameter models | 1-Year Warranty