Showing 97–108 of 120 systems
SKU: 609704
64× 400G OSFP (NDR) · 51.2 Tb/s · InfiniBand NDR · Sub-600 ns port-to-port
Fits GPU scale-out fabric
SKU: 842306
384 GB GDDR6 (8× 48 GB) · 4× Intel Xeon 6 · 1 TB DDR5 ECC · 80 TB NVMe · 2× 25 GbE
Self-contained AI micro data center
Fits Edge inference
SKU: 729618
768 GB GDDR7 (8× 96 GB) · 4× Intel Xeon 6 · 1 TB DDR5 ECC · 160 TB NVMe · 2× 25 GbE
Self-contained AI micro data center
Fits 70B local
SKU: 695950
768 GB GDDR7 (8× 96 GB) · 2× Intel Xeon 6 · 2 TB DDR5 ECC · 30 TB NVMe · 2× 100 GbE
High-density inference fleet
Fits 70B+ at scale
SKU: 598465
Up to 80 kW (cold-plate) · Direct-to-chip DLC · Manifold-fed (quick-disconnect) · 1 rack
Fits Direct-to-chip liquid cooling
SKU: 673911
Priority support · 4-hour onsite response (business hours) · Pan-India metro and tier-2 cities · 1–5 years
Fits Onsite support & AMC
SKU: 930534
Priority AMC · Same-day / 8-business-hour onsite response · Pan-India · 1–5 years
Fits Onsite support & AMC
SKU: 395109
Assignable from up to 128 GB unified pool · AMD Ryzen AI Max+ 16-core @ 85 W TBP · Up to 128 GB LPDDR5X-8000 (4 channels) · M.2 NVMe (config at quote) · Wi-Fi · USB-C · integrated (config at quote)
Mobile on-device AI fleet
Fits ~120B at 4-bit
SKU: 395103
Up to 96 GB assignable from 128 GB unified · AMD Ryzen AI Max+ 395 (16C / 32T) @ 147 W · Up to 128 GB LPDDR5X-8000 (256-bit) · 2× M.2 2280 NVMe PCIe 4.0 ×4 · 2.5GbE · Wi-Fi 7 · USB4 · HDMI 2.1 · DP 1.4
Sustained desk-side AI inference
Fits ~120B at 4-bit
SKU: 395104
Up to 96 GB assignable from 128 GB unified · AMD Ryzen AI Max+ 395 (16C / 32T) · Up to 128 GB LPDDR5X-8000 (256-bit) · 2× M.2 2280 NVMe PCIe 4.0 ×4 · 2.5GbE · Wi-Fi 7 · USB4 · HDMI 2.1 · DP 1.4
All-day desk-side AI workstation
Fits ~120B at 4-bit
SKU: 395106
5 bays · 10GbE RJ45 · USB 3.2 Gen2 · DP 1.4
AI-native network storage
Fits RAG / retrieval workloads
SKU: 395107
Up to 96 GB assignable from 128 GB unified · AMD Ryzen AI Max+ 395 (16C / 32T) · Up to 128 GB LPDDR5X-8000 (256-bit) · M.2 NVMe + optional 6× SATA daughterboard · 2.5GbE · USB4 · optical / Oculink rear-I/O options
Expandable edge inference
Fits ~120B at 4-bit
Showing 97–108 of 120 systems 