NVIDIA GeForce RTX 5080 16GB Specs, Benchmarks & Pricing
The NVIDIA GeForce RTX 5080 was the first GeForce RTX 50 series product that was launched using the GB203 GPU. NVIDIA unveiled the GeForce RTX 50 Series GPUs on January 6, 2025, powered by the Blackwell architecture, featuring advanced AI and ray tracing capabilities. RTX 50 Series GPUs support 5th Gen Tensor Cores.
Other key features include DLSS 4 which uses AI to generate up to three additional frames per traditionally rendered frame boosting frame rates, and the RTX Neural Shaders integrate small AI networks into the shading process, enabling higher quality rendering. RTX Neural Faces uses generative AI to create highly realistic digital human faces. NVIDIA ACE empowers game characters with AI-driven perception, planning, and action. These GPUs are designed for gamers, creators, and developers, offering significant performance gains over the RTX 40 series for AI, lifelike in-game characters and AI-powered creative tools. The GeForce RTX 5090 is the flagship model of the RTX 50 series and will be available on January 30th 2025, with other models following in the coming months.
Cheaper options in the RTX 50 series, including the RTX 5070 and RTX 5080.
- Release Date: January 30, 2025
- MSRP: $999 USD
- GPU Architecture: blackwell
- Hardware-Accelerated GEMM Operations:FP64 FP32 TF32 BF16 FP16 FP8 FP4 INT8 INT4
- CUDA Compute Capability : 12.8
Strengths
- Excellent FP32 compute performance (top 14% of GPUs)
- Excellent FP16 compute performance (top 17% of GPUs)
- Strong 3DMark Wild Life Extreme (4K) performance (top 5% of GPUs)
- Strong Counter-Strike 2 (4K) performance (top 13% of GPUs)
Specifications for NVIDIA GeForce RTX 5080
| Specification | Performance Ranking |
|---|---|
| FP32 TFLOPs | |
| FP16 TFLOPs | |
| Tensor Core Count | |
| Memory Capacity (GB) | |
| Memory Bandwidth (GB/s) | |
| Int8 TOPs | |
| FP8 TFLOPs | Data not available |
| FP4 TFLOPs |
Gaming Benchmarks for NVIDIA GeForce RTX 5080
Rankings based on 699,753 real-world benchmark results from OpenBenchmarking.org
| Benchmark | Performance Ranking |
|---|---|
| 3DMark Wild Life Extreme (4K) | |
| Counter-Strike 2 (4K) | |
| FurMark (GL) (4K) | |
| FurMark (GL) (1440p) | |
| FurMark (GL) (1080p) | |
| FurMark (VK) (4K) | |
| FurMark (VK) (1440p) | |
| FurMark (VK) (1080p) | |
| Quake II RTX (4K) |
Real-time NVIDIA GeForce RTX 5080 GPU Prices
Compare Price/Performance to other GPUs
Compare NVIDIA GeForce RTX 5080 to Another GPU
Price History
NVIDIA GeForce RTX 5080 Price History
This chart tracks NVIDIA GeForce RTX 5080 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 up 24.6%. The current lowest average is $1,452, compared to a typical $1,188 over the period. The lowest average price is calculated as the average of the three lowest-priced listings each day.
Product Identifiers
Manufacturer Part Numbers (4)
- Product SKU
- PG144/147 SKU 45
- Board ID
- PG147
- GPU DIE
- GB203-400-A1
- NVIDIA Part Number
- 900-1G144-2545-000
Available from 7 Partners (19 products)
- ROG Astral GeForce RTX 5080 OC Edition
- ROG-ASTRAL-RTX5080-O16G-GAMING(model number)
- TUF Gaming GeForce RTX 5080 OC
- TUF-RTX5080-O16G-GAMING(model number)
- PRIME GeForce RTX 5080 OC Edition
- PRIME-RTX5080-O16G(model number)
- PRIME GeForce RTX 5080
- PRIME-RTX5080-16G(model number)
- GeForce RTX 5080 16G GAMING TRIO OC
- G5080-16GTC(model number)
- GeForce RTX 5080 16G SUPRIM LIQUID SOC
- G5080-16SLS(model number)
- GeForce RTX 5080 16G VANGUARD SOC
- G5080-16VGS(model number)
- GeForce RTX 5080 16G VENTUS 3X OC PLUS
- G5080-16V3CP(model number)
- GeForce RTX 5080 GAMING OC 16G
- GV-N5080GAMING OC-16GD(model number)
- GeForce RTX 5080 AORUS MASTER ICE 16G
- GV-N5080AORUSM ICE-16GD(model number)
- GeForce RTX 5080 WINDFORCE SFF 16G
- GV-N5080WF3-16GD(model number)
- GeForce RTX 5080 WINDFORCE OC SFF 16G
- GV-N5080WF3OC-16GD(model number)
- GeForce RTX 5080 OC Triple Fan
- VCG508016TFXPB1-O(model number)
- GeForce RTX 5080 ARGB OC Triple Fan
- VCG508016TFXXPB1-O(model number)
- GAMING GeForce RTX 5080 AMP Extreme INFINITY
- ZT-B50800B-10P(model number)
- GAMING GeForce RTX 5080 SOLID OC
- ZT-B50800J-10P(model number)
- GeForce RTX 5080 GamingPro OC
- NE75080S19T2-GB2031A(model number)
- GeForce RTX 5080 GameRock
- NE75080019T2-GB2030G(model number)
- GeForce RTX 5080 Phoenix
- NE75080019T2-GB2031X(model number)
References
- https://images.nvidia.com/aem-dam/Solutions/geforce/blackwell/nvidia-rtx-blackwell-gpu-architecture.pdf
- https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5080/
- https://www.nvidia.com/en-us/geforce/graphics-cards/compare/
- https://nvidianews.nvidia.com/news/nvidia-blackwell-geforce-rtx-50-series-opens-new-world-of-ai-computer-graphics
- https://arxiv.org/abs/2310.16836
- https://www.tomshardware.com/pc-components/gpus/nvidia-blackwell-architecture-deep-dive-a-closer-look-at-the-upgrades-coming-with-rtx-50-series-gpus
- https://www.techpowerup.com/gpu-specs/geforce-rtx-5080.c4217
- https://videocardz.com/nvidia/geforce-50/geforce-rtx-5080
- https://pcpartpicker.com/product/87WmP6/nvidia-founders-edition-geforce-rtx-5080-16-gb-video-card-900-1g144-2545-000
- https://www.asus.com/us/motherboards-components/graphics-cards/prime/prime-rtx5080-o16g/
- https://us-store.msi.com/RTX-5080
- https://www.gigabyte.com/Graphics-Card/GV-N5080GAMING-OC-16GD
- https://www.pny.com/geforce-rtx-5080-models
- https://www.zotac.com/us/product/graphics_card/zotac-gaming-geforce-rtx-5080-amp-extreme-infinity
- https://www.palit.com/palit/vgapro.php?id=5395&lang=en
- https://www.gainward.com/main/vgapro.php?id=1229&lang=en
Notes
- We use the peak TOPS/FLOPS specs using the sparsity feature.
- Blackwell GB203 is the chip
- fp16TFLOPS is "Peak FP16 Tensor TFLOPS with FP16 Accumulate" as that's what NVIDIA publishes.
- int8TOPS of 450.2 represents non-sparse (dense) INT8 performance, derived from sparse INT8 of 900.4 TOPS ÷ 2 per NVIDIA Blackwell architecture whitepaper. With 2:4 structured sparsity, INT8 performance is 900.4 TOPS. Dense value used for consistent cross-vendor comparison.
- fp32TFLOPS is "Peak TF32 Tensor TFLOPS1" as published in the blackwell gpu architecture pdf.
- MSRP of $999 USD for the Founders Edition sourced from nvidia.com official press release (https://nvidianews.nvidia.com/news/nvidia-blackwell-geforce-rtx-50-series-opens-new-world-of-ai-computer-graphics).
- Manufacturer identifiers sourced from VideoCardz.com and TechPowerUp GPU Database, which report the RTX 5080 uses PG144/147 SKU 45 board and GB203-400-A1 GPU die. Founders Edition NVPN (900-1G144-2545-000) sourced from PCPartPicker and Best Buy retail listings.
- Third-party products represent major AIB partners (ASUS, MSI, Gigabyte, PNY, Zotac, Palit, Gainward). Model numbers sourced from manufacturer websites, retail listings (Best Buy, Micro Center, Newegg), and TechPowerUp GPU Database. Note that EVGA exited the graphics card business in 2022 and does not produce RTX 5080 cards.
- fp4TFLOPS of 900.5 represents non-sparse (dense) FP4 performance, derived from the official NVIDIA AI TOPS figure of 1801 (FP4 sparse, per nvidia.com/en-us/geforce/graphics-cards/compare/) ÷ 2. Dense value used for consistent cross-vendor comparison.
- NOT FOUND: fp8TFLOPS — NVIDIA does not publish a standalone dense or sparse FP8 TFLOPS figure for consumer GeForce Blackwell cards; searched the NVIDIA RTX Blackwell architecture whitepaper and the official RTX 5080 product/compare pages (URLs in references), which list only AI TOPS (FP4 sparse), Peak TF32 Tensor TFLOPS, Peak FP16 Tensor TFLOPS, and INT8 TOPS. Left null rather than guessed from the INT8 dense value.
- supportedHardwareOperations: INT4 removed per the locked GEMM-only definition (2026-09) — neither the consumer nor datacenter Blackwell documentation lists INT4 Tensor Core support (dropped starting with Blackwell per gpu-researcher.md's canonical Blackwell table); the array now matches the canonical consumer Blackwell baseline of FP4, FP8, FP16, BF16, TF32, INT8.