GeForce RTX 3090
The GeForce RTX 3090 is Nvidia’s 24GB graphics card with a 350W board power rating, built on the Ampere GA102 architecture. Below you’ll find its full spec sheet and gaming and productivity benchmarks, plus all 1 board version we track, each with its cheapest current price in Germany.
Prices update regularly and may differ at the retailer. This page contains affiliate links.
Prices include 19% VAT. Shipping is shown under each price, and offers are listed by price plus shipping.
Gaming performance
Gaming score: geometric mean of in-game FPS, normalized so the RTX 5090 = 100. Render and synthetic scores are in the Benchmarks section below.
Gaming scores are normalised performance indexes derived from Tom’s Hardware’s published GPU benchmarks. Performance per dollar and per watt are our own calculations on top of that data.
1080p Gaming
1440p Gaming
4K Gaming
The GeForce RTX 3090 scores 67.0 at 1080p, 48.4 at 1440p, and 38.3 at 4K on a scale where 100 = the fastest GPU we test (RTX 5090). These scores apply to all board versions of this chip.
Performance-per-euro rank among all GPUs with live pricing in Germany
Value at 1080p
#26
Value at 1440p
#26
Value at 4K
#22
Benchmarks
Standardized benchmark scores for this chip, each compared to the fastest card we track and linked to its source. They apply to every board version.
3D & gaming
Render
Compute & AI
GeForce RTX 3090 versions (1)
Every board version we track, cheapest first.
- GALAX RTX 3090 Turbo295 mm€4,249.66Free shipping
| Version | Boost Clock | Length | Color | From | Buy | |
|---|---|---|---|---|---|---|
| GALAX RTX 3090 Turbo | — | 295 mm | — | €4,249.66 Free shipping | |
1 board version of the GeForce RTX 3090 are listed above, starting from €4,249.66. Prices update daily from live retailer stock. Click any version name for its full spec sheet and all current retailer prices. Prices include 19% VAT. Shipping is shown under each price, and offers are listed by price plus shipping.
Specifications
Every GeForce RTX 3090 board version we track measures 295 mm long.
Performance
- Boost clock
- 1695 MHz
- Base clock
- 1395 MHz
- Shader cores
- 10,496
- SM count
- 82
- Texture units (TMUs)
- 328
- Render outputs (ROPs)
- 112
- RT cores
- 82 · 2nd gen
- Tensor / AI cores
- 328 · 3rd gen
Memory
- VRAM
- 24GB GDDR6X
- Memory bus
- 384-bit
- Bandwidth
- 936 GB/s
- Memory speed
- 19.5 Gbps
- L2 cache
- 6 MB
GPU die
- Architecture
- Ampere GA102
- Process node
- Samsung 8N
- Foundry
- Samsung
- Die size
- 628 mm²
- Transistors
- 28.3 billion
- Generation
- GeForce RTX 30
Power
- TDP
- 350W
- Recommended PSU
- 750W
- Power connectors
- 1 12-pin
Display & outputs
- Max resolution
- 7680 × 4320
- Max displays
- 4
- HDCP
- 2.3
- Outputs
- 1 HDMI 2.1, 3 Displayport 1.4a
- PCIe interface
- PCIe 4.0 ×16
APIs & software
- DirectX
- 12 Ultimate (12.2)
- Vulkan
- 1.3
- OpenGL
- 4.6
- OpenCL
- 3.0
- CUDA
- Compute 8.6
- Shader model
- 6.8
Video encoding & decoding
| Codec | Encode | Decode |
|---|---|---|
| H.264 / AVC | Supported | Supported |
| H.265 / HEVC | Supported | Supported |
| AV1 | Not supported | Supported |
| VP9 | Not supported | Supported |
Encoder: NVENC 7th gen · Decoder: NVDEC 5th gen
Features
- Upscaling
- DLSS Super Resolution, Ray Reconstruction
- Also runs
- FSR 3, FSR 3 Frame Generation, XeSS 2, XeSS 2 Frame Generation
- Resizable BAR
- Yes
- Multi-GPU
- NVLink
Physical
- Reference length
- 336 mm
- Slot width
- 3 slots
- Released
- 2020-09-24
10,496 shader cores feed a 384-bit memory interface delivering 936 GB/s of peak bandwidth. 82 RT cores handle real-time ray tracing; 328 tensor cores accelerate AI workloads and DLSS Super Resolution. Compare the GeForce RTX 3090 against the full GPU lineup on the full graphics card rankings.
Local AI performance
What the GeForce RTX 3090 can run on your own machine, and how fast.
Largest model it can run (8K context)
- Q4 (the usual choice, near-original quality)
- ~32B
- Q8 (closer to original, half the model size)
- ~19B
- FP16 (unquantised, for training and research)
- ~10B
Parameter counts the card holds with room for an 8K conversation, counting the model weights plus its attention cache. A longer conversation needs more memory, so it lowers these figures.
Speed & value
- Speed, 8B model at Q4
- 121-142 tok/s
- Memory bandwidth
- 936 GB/s
- Price per GB of VRAM
- €177.07
Generation speed tracks memory bandwidth, because every word produced reads the whole model from memory. Shown as a range.
Models that fit, at Q4
| Model | Size | Memory needed | Est. speed |
|---|---|---|---|
| Llava 34B | 34.8B | 21.5GB | 30-36 tok/s |
| Yi 34B | 34.4B | 21.5GB | 30-36 tok/s |
| Nous Hermes2 34B | 34.0B | 21.6GB | 30-36 tok/s |
Popular models small enough for this card at Q4, one per family. Speed is left blank for mixture-of-experts models, where a bandwidth estimate is not reliable enough to publish.
Choosing a card for AI? Compare every GPU for local AI, including setups that pool the memory of two or more cards.
Across generations
Where the GeForce RTX 3090 sits in Nvidia’s lineup — the generation before and after.
How the GeForce RTX 3090 compares
Similar cards worth a look, based on live prices in Germany and 1440p gaming performance. Open a card for its full spec sheet.
Affiliate disclosure: Some links on this page are affiliate links — MaxMyBuild may earn a commission at no extra cost to you if you buy through them. As an Amazon Associate, MaxMyBuild earns from qualifying purchases. For Amazon, current price and availability are shown on the Amazon product page; product prices and availability are accurate as of the date and time of purchase and are subject to change. Prices shown for other retailers are approximate and may differ at checkout. “Search” links are non-affiliate and provided for convenience only.