NVIDIA Quadro RTX 5000 16GB
Overview
The NVIDIA Quadro RTX 5000 is the TU104 member of NVIDIA's first ray tracing workstation family, with 3,072 CUDA cores, 384 second-generation Tensor cores and 48 RT cores, and 16 GB of GDDR6 with ECC on a 256-bit bus at 448 GB/s. It delivers 11.2 TFLOPS of FP32 and 89.2 TFLOPS of FP16 tensor throughput, and unlike the GeForce Turing cards it takes no penalty for accumulating in FP32: NVIDIA's whitepaper prints 89.2 for both accumulate widths, which is the professional exemption that also applies to the Quadro RTX 6000. Two cards bridge over NVLink at 50 GB/s for 32 GB of pooled memory. It still shows up on rental marketplaces and second-hand, where 16 GB with ECC at a low hourly rate remains useful for small-model inference, though there is no BF16, TF32 or FP8 on this generation.
Performance
Peak theoretical throughput by precision type
| Precision | Peak |
|---|---|
FP64 64-bit floating point | 0.3TFLOPS |
FP32 32-bit floating point | 11TFLOPS |
TF32 | No verified data available |
BF16 | No verified data available |
FP16 16-bit floating point | 89TFLOPS |
FP8 | No verified data available |
FP6 | No verified data available |
FP4 | No verified data available |
INT8 8-bit integer | 178TOPS |
INT4 4-bit integer | 357TOPS |
Every figure here is dense. The vendor documents no structured (2:4) sparsity mode for this part, so there is no second number to quote.
Per watt divides the dense figure by the 265 W board power. Where only a sparse figure exists, the cell says so.
The Quadro RTX 5000 16GB in the GPU landscape
Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper
Higher and further left is better: more half-precision throughput for less power.
Specifications
Architecture
Turing
Form Factor
PCIe
Launch Year
2018
Process Node
12nm
Memory
16 GB GDDR6
Bandwidth
448 GB/s
TDP
265 W
Max Power
265 W
Transistors
13.6 billion
Interconnect
50 GB/s NVLink
CUDA Cores
3,072
Spec Confidence
Official
Full Specifications
| Compute Engine | |
|---|---|
| CUDA Cores | 3,072 |
| Tensor Cores | 384 (Turing) |
| Streaming Multiprocessors | 48 |
| Base Clock | 1.62 GHz |
| Boost Clock | 1.81 GHz |
| Chip Design | |
| Transistors | 13.6 billion |
| Die Size | 545 mm² |
| Process Node | 12nm |
| Memory | |
| VRAM | 16 GB |
| Memory Type | GDDR6 |
| Bandwidth | 448 GB/s |
| Interface Width | 256-bit |
| Memory Clock | 14 GT/s |
| Interconnect & I/O | |
| GPU-to-GPU | NVLink |
| Interconnect Bandwidth | 50 GB/s |
| Interconnect Links | 2 |
| PCIe | 3.0 x16 |
| Cache | |
| L2 Cache | 4 MB |
| Power & Thermal | |
| TDP | 265 W |
| Max Board Power | 265 W |
| Cooling | Active |
| Enterprise Features | |
| ECC Memory | Yes |
| Sparsity | No |
| Compute APIs | CUDA, DirectCompute, OpenCL |
| Physical & Media | |
| Card Length | 266.7 mm |
| Width | 2-slot |
| NVENC Engines | 1 |
| NVDEC Engines | 2 |
| General | |
| Form Factor | PCIe |
| Architecture | Turing |
| Process Node | 12nm |
| Launch Year | 2018 |
Datasheet & Resources
Flopper Datasheet
NVIDIA Quadro RTX 5000 16GB specifications, generated from our database. Printable.
Vendor product page
NVIDIA documentation for the Quadro RTX 5000 16GB
NVIDIA Quadro RTX 5000 Data Sheet
NVIDIA · 2019-03-01
NVIDIA Developer Documentation
Technical specs, programming guides
Data Provenance
Every figure traced to a source
Primary Source
- Document
- NVIDIA Quadro RTX 5000 Data Sheet
- Publisher
- NVIDIA
- Published
- 2019-03-01
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Core precisions with figures
- 4 of 9
- Normalization
- All values in TFLOPS
Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.
Browse GPU Cloud ProvidersSimilar GPUs
Frequently Asked Questions
How many TFLOPS does the NVIDIA Quadro RTX 5000 have?
The NVIDIA Quadro RTX 5000 delivers 11 TFLOPS FP32 and 89 TFLOPS FP16 at peak. Flopper does not currently have a verified FP8 throughput figure for it.
What is the power consumption of the NVIDIA Quadro RTX 5000?
The NVIDIA Quadro RTX 5000 has a TDP (Thermal Design Power) rating of 265 watts.
How much memory does the NVIDIA Quadro RTX 5000 have?
The NVIDIA Quadro RTX 5000 is equipped with 16 GB of VRAM with 448 GB/s of memory bandwidth.
What architecture is the NVIDIA Quadro RTX 5000 based on?
The NVIDIA Quadro RTX 5000 is based on the Turing architecture, launched in 2018.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.