Kentino
NVIDIA GeForce RTX 4090 24 GB GDDR6X (Refurbished)
NVIDIA GeForce RTX 4090 24 GB GDDR6X (Refurbished)
Не може да се зареди възможността за взимане
NVIDIA GeForce RTX 4090 — 24 GB for on-prem AI
A professionally refurbished RTX 4090: 24 GB of GDDR6X and Ada Lovelace compute, tested and verified stable under sustained load. The workhorse card for multi-GPU LLM inference and workstation AI at a fraction of datacenter-GPU cost.
The 24 GB workhorse for AI inference
The RTX 4090 pairs 24 GB of GDDR6X with 16,384 Ada Lovelace CUDA cores and 4th-gen Tensor cores — enough VRAM to serve quantized 7B–13B models comfortably, or to run a 70B-class model across two to four cards. It is the price-performance backbone of Kentino's multi-GPU AI builds. Each refurbished unit is cleaned, inspected and stress-tested before it ships.
Technical data
| GPU | NVIDIA AD102 — Ada Lovelace |
| Memory | 24 GB GDDR6X, 384-bit |
| Memory bandwidth | ~1,008 GB/s |
| CUDA cores | 16,384 |
| Tensor cores | 512 (4th gen) · up to ~330 TFLOPS FP16 |
| RT cores | 128 (3rd gen) |
| Interface | PCIe 4.0 ×16 |
| Board power | 450 W (16-pin 12VHPWR) |
| Condition | Refurbished — bench-tested, verified stable |
Where it fits
- On-prem LLM inference — 24 GB hosts quantized 7B–13B models; scale to 70B across multiple cards.
- AI workstations and fine-tuning of small-to-mid models.
- Rendering, simulation and content-creation workloads.
- Cost-effective multi-GPU servers where datacenter GPUs are overkill.
FAQ
What does "refurbished" mean here?
The card has been professionally cleaned, visually inspected and stress-tested for stability and full VRAM function before dispatch. It is not a new retail unit.
Can it run a 70B model?
Not on a single card — a 70B model at 4-bit needs ~40 GB of VRAM. Two to four RTX 4090 (48–96 GB total) handle it via tensor-parallel inference.
Does it fit a standard server?
The RTX 4090 is a large triple-slot card. It fits tower and 4U rack builds; confirm slot clearance and 16-pin power availability in your chassis.