- Joined
- Oct 9, 2007
- Messages
- 47,931 (7.37/day)
- Location
- Dublin, Ireland
System Name | RBMK-1000 |
---|---|
Processor | AMD Ryzen 7 5700G |
Motherboard | Gigabyte B550 AORUS Elite V2 |
Cooling | DeepCool Gammax L240 V2 |
Memory | 2x 16GB DDR4-3200 |
Video Card(s) | Galax RTX 4070 Ti EX |
Storage | Samsung 990 1TB |
Display(s) | BenQ 1440p 60 Hz 27-inch |
Case | Corsair Carbide 100R |
Audio Device(s) | ASUS SupremeFX S1220A |
Power Supply | Cooler Master MWE Gold 650W |
Mouse | ASUS ROG Strix Impact |
Keyboard | Gamdias Hermes E2 |
Software | Windows 11 Pro |
Sapphire introduced its Radeon AI PRO R9700 professional graphics card. Sapphire's take on the PRO R9700 is very similar to a custom design by ASUS, and comes with a design that favors workstation deployments with up to four of these cards installed next to each other. The card is 26.6 cm in length, strictly 2 slots thick, and 11.1 cm tall, or strictly what constitutes "full height," making it fit for 3U rackmount cases. Helping its enterprise chops are a 12V-2x6 power input located at the tail end of the card instead of on the top; and rear bracket mounting holes that help you secure the card to the chassis using expanders.
The card features a lateral airflow blower-based cooling solution. The PCB and cooler shroud has cutouts on the reverse side of the card, where the backplate is recessed, to help adjacent cards better take in airflow. The Radeon AI PRO R9700 targets both professional visualization and edge AI acceleration use-cases. It is based on a maxed out 4 nm "Navi 48" silicon, just like the desktop Radeon RX 9070 XT, but with double the memory size at 32 GB, so it could accelerate larger LLMs. The GPU offers a peak INT4 throughput of 1,531 TOPS, and peak FP16 throughput of 95.7 TFLOP/s.

View at TechPowerUp Main Site | Source
The card features a lateral airflow blower-based cooling solution. The PCB and cooler shroud has cutouts on the reverse side of the card, where the backplate is recessed, to help adjacent cards better take in airflow. The Radeon AI PRO R9700 targets both professional visualization and edge AI acceleration use-cases. It is based on a maxed out 4 nm "Navi 48" silicon, just like the desktop Radeon RX 9070 XT, but with double the memory size at 32 GB, so it could accelerate larger LLMs. The GPU offers a peak INT4 throughput of 1,531 TOPS, and peak FP16 throughput of 95.7 TFLOP/s.




View at TechPowerUp Main Site | Source