
Pictured: Fractal Design Meshify 2 XL (Black, light-tint glass), shown empty, and NVIDIA GeForce RTX 3090 Founders Edition. Refurbished cards may be partner models.
CG AI Duo 48 Workstation (2x RTX 3090)
Black Friday price: you save $290.62 until Dec 1. No code needed.
Paid in Bitcoin, Monero, USDT or another coin you choose.
Free insured shipping. US delivery in about 5 to 11 business days. Shipping details
Overview
CG AI Duo 48 puts two refurbished RTX 3090s, 24GB each, on an ASRock X870E Taichi, the AM5 board whose two x16 slots sit four slots apart so the cards are not pressed together. A Ryzen 7 9700X, 64GB of DDR5, a Corsair HX1500i and a Fractal Meshify 2 XL complete the build.
Each card has 936GB/s of memory bandwidth, and the 48GB total holds a 70B model at 4-bit (about 40GB) or a 32B model at 8-bit with moderate context. Software splits the layers across the two cards, so generation runs at the pace of one card at a time rather than doubling. CUDA means llama.cpp, vLLM and Ollama run without extra work.
The trade-offs are age and heat. The 3090 is a 2020 design rated at 350W per card, so a pair needs the large case and 1500W supply listed here, and these cards are refurbished rather than new. Ampere also has no native FP8 or FP4 support, which newer RTX cards add.
- 2x RTX 3090, 48GB VRAM total
- 936GB/s memory bandwidth per card
- Four-slot gap between GPU slots
- 1500W power supply
Specifications
| Graphics cards | 2x NVIDIA GeForce RTX 3090, 24GB GDDR6X each (refurbished, tested) |
|---|---|
| Total VRAM | 48GB (2 x 24GB), 384-bit bus per card |
| Memory bandwidth | 936GB/s per card |
| GPU details | Ampere, 10,496 CUDA cores and 3rd-generation Tensor cores per card, 350W reference board power |
| Processor | AMD Ryzen 7 9700X, 8 cores / 16 threads, up to 5.5GHz boost, 32MB L3, 65W TDP |
| Memory | 64GB DDR5 (2 x 32GB), up to DDR5-5600 with two modules |
| Storage | NVMe SSD, capacity confirmed with your order |
| Local AI capacity | 70B at 4-bit, 32B at 8-bit, layers split across both cards |
| Motherboard | ASRock X870E Taichi, E-ATX, AM5, 4 DIMM slots, 5GbE, Wi-Fi 7 |
|---|---|
| GPU slots | Two PCIe 5.0 x16 slots four slots apart, x8/x8 with both populated; each 3090 links at PCIe 4.0 x8 |
| Cooling | Arctic Freezer 36, dual tower, 2x P12 PWM PST fans, 159mm tall |
| Power supply | Corsair HX1500i (2025), 1500W, ATX 3.1, Cybenetics Platinum, 10-year warranty |
| Case | Fractal Design Meshify 2 XL, 9 expansion slots, up to 530mm GPU length, 185mm cooler clearance |
|---|---|
| Case fans | 3x Dynamic X2 GP-14 preinstalled |
| Front I/O | 2x USB-A 5Gbps, 1x USB-C 20Gbps, audio and microphone jacks |
| Networking | 5Gbit Ethernet and Wi-Fi 7 with Bluetooth 5.4 on the motherboard |
| Operating system | Ubuntu 24.04 with Ollama, llama.cpp and Open WebUI, Ubuntu 24.04 with open models preloaded, or Windows 11 Pro (+$189.05) |
|---|---|
| Warranty | 3-year parts, lifetime support |
Questions and answers
Still unsure? Visit the help center or message us.
Do the two cards act as one 48GB GPU?
Not as a single device. llama.cpp, vLLM and Ollama divide a model across the cards, so a 40GB model fits, but each card still holds only its own 24GB and the context cache is split too.
How fast can a 70B model generate?
Each token reads all the weights, and at 936GB/s a 40GB model has a ceiling near 23 tokens per second when the layers run one card after the other. Real speeds are lower than that ceiling.
Do two 3090s fit side by side?
The Taichi leaves four slots between its x16 slots. NVIDIA's own 3090 is a 3-slot, 313mm card, and we choose partner models no thicker than that.
Is an NVLink bridge included?
No. The 3090 supports NVLink, but inference software splits models over PCIe, and this build runs each card at PCIe 4.0 x8 from the CPU's x8/x8 slots.
Are the refurbished cards covered by warranty?
Yes. The cards are tested before assembly and covered by the same 3-year parts warranty and lifetime support as the rest of the build.
From the blog
Pairs well with
Picked to go with this product. Check sizes and connectors for your build before you order.








