Skip to content
SlayDots

XC100 AI workstation, domestic (Stellar)

Photo coming soon

XC100 AI workstation, domestic (Stellar)

AI GPU workstations and servers · Model XC100

Not yet quoted

Minimum orderNot yet quoted

Key facts

  • Series tagline: Liquid Cooling · Silent OperationSupplier claim
  • Badge: CNSupplier claim
See all 24 facts

These details are supplier claims. We haven't tested them yet.

Specifications

  • Series tagline: Liquid Cooling · Silent OperationSupplier claim
  • Badge: CNSupplier claim
  • Variant 1 label: Zhaoxing SolutionSupplier claim
  • CPU (Zhaoxing): Zhaoxin KX-7000Supplier claim
  • GPU (Zhaoxing): Moore Threads MTT S80Supplier claim
  • RAM (Zhaoxing): 32GB DDR4 (Expandable to 64GB)Supplier claim
  • I/O (Zhaoxing): 4*USB3.0 Type-A 2*USB2.0 Type-ASupplier claim
  • Video Output (Zhaoxing): • 1×DP 1.4 • 1×HDMI®2.0 • 1×VGASupplier claim
  • Network I/O (Zhaoxing): • 3×RJ45 2.5GSupplier claim
  • Variant 2 label: Hygon SolutionSupplier claim
  • CPU (Hygon): Hygon 3450GSupplier claim
  • GPU (Hygon): MetaX N260Supplier claim
  • RAM (Hygon): 64GB DDR5Supplier claim
  • I/O (Hygon): 4*USB3.0 Type-ASupplier claim
  • Video Output (Hygon): • 1×HDMI®2.0 • 1×VGASupplier claim
  • Network I/O (Hygon): • WiFi 6 + BT 5.2 • 4×RJ45 2.5GSupplier claim
  • ROM: PCIe 4.0 + Dual M.2 2280 (both)Supplier claim
  • GPU compute: MuXi N260: 280 TOPS (INT8) | Moore Threads MTT S80: 14.7 TFLOPS (FP32)Supplier claim
  • GPU compatibility: Compatible with MetaX N260 And Moore Threads MTT S80; NVIDIA Pro 6000 / Pro 5000Supplier claim
  • Headline: Up to 96GB Total VRAM | 4,000 TOPS (Theoretical Peak)Supplier claim
  • Chassis Volume: 11L 320*136*250mm mmSupplier claim
  • Real-World Benchmark: XC100 Mortex N260 Qwen3.6-35B Performance: Model | Inference Framework | Quantization | Single-Concurrency Peak | Multi-Concurrency Peak | Max Context Length | ITL Latency ;; Qwen3.6-35B-A3B-W8A8 / vLLM / W8A8 / 21.60 / 611 / 256K / 19~936msSupplier claim
  • Peak throughput under extreme context length (Single-concurrency, output=64). Unit: tok/s: Model | 128 | 256 | 512 | 1k | 2k | 4k | 8k | 16k | 32k | 64k | 128k | 256k ;; Qwen3.6-35B-A3B-W8A8 / 21.60 / 21.58 / 21.32 / 20.72 / 19.99 / 17.93 / 14.70 / 10.28 / 5.78 / 2.54 / 0.89 / 0.28Supplier claim
  • Multi-Stream Throughput (Single-Stream Ref: input=512, output=64, tok/s): Model | Concur=1 | Concur=2 | Concur=4 | Concur=8 | Concur=16 | Concur=32 | Concur=64 | Stream Peak ;; Qwen3.6-35B-A3B-W8A8 / 21.32 / 86.23 / 140.24 / 189.97 / 278.64 / 346.56 / 376.10 / 376.10Supplier claim

Goods price for one unit

What you pay

Goods price: what you pay now

Prices in MYR

  • XC100 AI workstation, domestic (Stellar)

    Not yet quoted

No total yet. Every item needs a confirmed price first.

Prices as of 02:03

How you pay
  • Now: the goods.
  • Later: shipping, import duty and import taxes, at our shipping agent's actual cost. We invoice them when your goods reach the agent, payment is due within 7 days, and then we deliver.
  • The shipping and duty range is an estimate, not a cap: you pay the actual cost, even outside the range.
  • Our shipping agent is the importer of record and passes import duty and taxes on at cost.
  • No sales tax is added to our prices.