NVIDIA RTX 2000 Ada Generation 16GB Specs, Benchmarks & Pricing

The NVIDIA RTX 2000 Ada Generation is an entry-level professional workstation GPU released in February 2024, built on the Ada Lovelace architecture using the AD107 chip with TSMC's 4N custom process. It features 2,816 CUDA cores, 88 fourth-generation Tensor Cores, and 22 third-generation RT Cores, paired with 16GB of GDDR6 ECC memory. The fourth-generation Tensor Cores introduce FP8 precision support and deliver 95.95 TOPS of dense INT8 performance (191.9 TOPS with sparsity), providing significant AI acceleration for professional workloads. With a TDP of only 70W and no external power connector required, the RTX 2000 Ada offers exceptional power efficiency in a compact dual-slot, low-profile form factor. The GPU delivers 12.0 TFLOPS of FP32 performance and 27.7 TFLOPS of RT Core performance. Memory bandwidth of 224 GB/s is provided through a 128-bit memory interface running at 14 Gbps effective speed. With PCI Express 4.0 x8 interface and four mini DisplayPort 1.4a outputs supporting up to 7680×4320 resolution at 60Hz, it's designed for professional visualization, CAD, 3D modeling, rendering, and AI/ML workloads in compact workstation environments.

  • Release Date: February 12, 2024
  • MSRP: $625 USD
  • GPU Architecture: ada
  • Hardware-Accelerated GEMM Operations:
    FP64 FP32 TF32 BF16 FP16 FP8 FP4 INT8 INT4
  • CUDA Compute Capability : 8.9

Considerations

  • Lower FP32 compute performance compared to other GPUs
  • Lower tensor core count compared to other GPUs
  • Below average 3DMark Wild Life Extreme (1080p) performance

Specifications for NVIDIA RTX 2000 Ada Generation

SpecificationPerformance Ranking
FP32 TFLOPs
14th @ 12 TFLOPs
FP16 TFLOPs
42nd @ 95.9 TFLOPs (Entry Tier)(Entry)
Tensor Core Count
15th @ 88 Cores
Memory Capacity (GB)
60th @ 16 GB (Mid Tier)(Mid)
Memory Bandwidth (GB/s)
7th @ 224 GB/s
Int8 TOPs
13th @ 95.95 TOPs
FP8 TFLOPs
3rd @ 95.95 TFLOPs
FP4 TFLOPsData not available

Gaming Benchmarks for NVIDIA RTX 2000 Ada Generation

Rankings based on 633 real-world benchmark results from OpenBenchmarking.org

BenchmarkPerformance Ranking
3DMark Wild Life Extreme (1080p)
13th @ 244 FPS

Real-time NVIDIA RTX 2000 Ada Generation GPU Prices

We're tracking 37 of the NVIDIA RTX 2000 Ada Generation GPUs currently available for sale. The lowest average price is $663 (what's this?)
Buy Now

Compare Price/Performance to other GPUs

We track real-time prices of other GPUs too so that you can compare the price/performance of the NVIDIA RTX 2000 Ada Generation GPU to other GPUs.
Compare GPU Price/Performance

Compare NVIDIA RTX 2000 Ada Generation to Another GPU

Compare the NVIDIA RTX 2000 Ada Generation directly to another GPU to see specs, benchmarks, and prices side-by-side.
Compare GPUs Side-by-Side

Price History

NVIDIA RTX 2000 Ada Generation Price History

This chart tracks NVIDIA RTX 2000 Ada Generation prices over the past 6 months based on eBay listings. The yellow line shows the average of the three lowest-priced listings each day—a useful indicator for finding deals.

Trend: Over this period, the lowest average price has been relatively stable. The current lowest average is $663. The lowest average price is calculated as the average of the three lowest-priced listings each day.

gpupoet.com

Product Identifiers

Manufacturer Part Numbers (1)
NVIDIA Part Number
900-5G192-2250-000
Available from 3 Partners (3 products)
PNY
NVIDIA RTX 2000 Ada Generation 16GB GDDR6 Graphics Card
VCNRTX2000ADA-PB(sku)
Dell
Dell NVIDIA RTX 2000 Ada Generation, 16 GB GDDR6, dual slot, low profile, PCIe 4.0x8, 4 mini DP Graphics Card
490-BKLT(part number)
Lenovo
NVIDIA RTX 2000 Ada 16GB mini-DP x4 GDDR6 Graphics Card
4X61Q50292(part number)

References

Notes

  1. FP32 TFLOPS of 12.0 sourced from NVIDIA official product page and confirmed by PNY product page.
  2. Tensor performance of 191.9 TFLOPS represents peak FP8 tensor performance with sparsity.
  3. FP16 TFLOPS of 95.9 represents Peak Sparse Tensor Core performance (calculated as half of FP8 Sparse performance). This metric is selected to align with the card's workstation AI capabilities.
  4. int8TOPS of 95.95 represents non-sparse (dense) INT8 performance, derived from sparse INT8 of 191.9 TOPS ÷ 2 per NVIDIA Ada Lovelace architecture. With 2:4 structured sparsity, INT8 performance is 191.9 TOPS. Dense value used for consistent cross-vendor comparison.
  5. fp8TFLOPS of 95.95 represents non-sparse (dense) FP8 performance, derived from the peak FP8 tensor performance of 191.9 TFLOPS with sparsity (per NVIDIA Ada Lovelace architecture, this file's pre-existing note) ÷ 2. NVIDIA's Ada Lovelace 4th-generation Tensor Cores process FP8 and INT8 at identical per-clock throughput (both are 8-bit formats), so dense FP8 (95.95) numerically equals dense INT8 (95.95). Dense value used for consistent cross-vendor comparison.
  6. Ada Lovelace has no FP4 hardware path (FP4 tensor core support was introduced in Blackwell) — fp4TFLOPS is left null and is a confirmed hardware negative, not a research gap, so it is not added to unverifiedSpecs.
  7. Memory bandwidth calculated as 128-bit interface × 14 Gbps ÷ 8 bits/byte = 224 GB/s.
  8. CUDA Compute Capability 8.9 is standard for Ada Lovelace architecture workstation GPUs.
  9. The GPU uses the AD107 chip with 22 of 24 SMs enabled, fabricated on TSMC 4N custom process.
  10. TDP is 70W, no external power connector required.
  11. MSRP of $625 USD positions it as the entry-level model in the Ada workstation lineup.
  12. supportedHardwareOperations corrected during the 2026-09-02 Phase 5 audit to remove FP32: per the canonical Ada Lovelace supportedHardwareOperations table (locked precision-filters plan definition, "hardware-accelerated matrix/tensor-core path support only"), FP32 is not a standalone Ada Tensor Core format — it only appears as plain shader/CUDA-core ALU throughput or as the TF32 reduced-precision tensor proxy. Canonical set is FP8, FP16, BF16, TF32, INT8, INT4, uniform across all Ada SKUs (GeForce, professional, and datacenter) per the NVIDIA Ada GPU Architecture whitepaper.
This site contains affiliate links. As an eBay Partner and Amazon Associate, gpupoet.com may be compensated if you make a purchase, at no cost to you. Learn more.