GeForce RTX 4070 Ti Super
The GeForce RTX 4070 Ti Super is Nvidia’s 16GB graphics card with a 285W board power rating, built on the Ada Lovelace AD103 architecture. Below you’ll find its full spec sheet and gaming and productivity benchmarks. No board versions are in stock right now, but the specs and benchmarks below still apply whenever it returns to retailers.
Prices update regularly and may differ at the retailer. This page contains affiliate links.
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 4070 Ti Super scores 80.8 at 1080p, 63.9 at 1440p, and 51.4 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-dollar rank among all GPUs with live pricing
Value at 1080p
—
Value at 1440p
—
Value at 4K
—
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 4070 Ti Super availability
Live retailer stock for this model.
Currently out of stock
None of the board versions of the GeForce RTX 4070 Ti Super are in stock at the retailers we track right now. Prices refresh daily, so check back — or compare in-stock alternatives below.
Browse in-stock graphics cardsSpecifications
The reference GeForce RTX 4070 Ti Super measures 310 mm long.
Performance
- Boost clock
- 2610 MHz
- Base clock
- 2340 MHz
- Shader cores
- 8,448
- SM count
- 66
- Texture units (TMUs)
- 264
- Render outputs (ROPs)
- 96
- RT cores
- 66 · 3rd gen
- Tensor / AI cores
- 264 · 4th gen
Memory
- VRAM
- 16GB GDDR6X
- Memory bus
- 256-bit
- Bandwidth
- 672 GB/s
- Memory speed
- 21 Gbps
- L2 cache
- 48 MB
GPU die
- Architecture
- Ada Lovelace AD103
- Process node
- TSMC 4N
- Foundry
- TSMC
- Die size
- 379 mm²
- Transistors
- 45.9 billion
- Generation
- GeForce RTX 40
Power
- TDP
- 285W
- Recommended PSU
- 700W
- Power connectors
- 1 16-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 8.9
- Shader model
- 6.8
Video encoding & decoding
| Codec | Encode | Decode |
|---|---|---|
| H.264 / AVC | Supported | Supported |
| H.265 / HEVC | Supported | Supported |
| AV1 | Supported | Supported |
| VP9 | Not supported | Supported |
Encoder: NVENC 8th gen · Decoder: NVDEC 5th gen
Features
- Upscaling
- DLSS Super Resolution, Ray Reconstruction, Frame Generation
- Also runs
- FSR 3, FSR 3 Frame Generation, XeSS 2, XeSS 2 Frame Generation
- Resizable BAR
- Yes
Physical
- Reference length
- 310 mm
- Slot width
- 3 slots
- Released
- 2024-01-24
- MSRP
- $799.00
8,448 shader cores feed a 256-bit memory interface delivering 672 GB/s of peak bandwidth. 66 RT cores handle real-time ray tracing; 264 tensor cores accelerate AI workloads and DLSS Super Resolution. Compare the GeForce RTX 4070 Ti Super against the full GPU lineup on the full graphics card rankings.
Local AI performance
What the GeForce RTX 4070 Ti Super can run on your own machine, and how fast.
Largest model it can run (8K context)
- Q4 (the usual choice, near-original quality)
- ~20B
- Q8 (closer to original, half the model size)
- ~12B
- FP16 (unquantised, for training and research)
- ~6.6B
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
- 93-109 tok/s
- Memory bandwidth
- 672 GB/s
- Price per GB of VRAM
- —
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 |
|---|---|---|---|
| GPT Oss 20B | 20.9B | 13.2GB | — |
| Granite Code 20B | 20.1B | 13.7GB | 37-43 tok/s |
| Starcoder2 15B | 16.0B | 9.7GB | 47-55 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.
Across generations
Where the GeForce RTX 4070 Ti Super sits in Nvidia’s lineup — the generation before and after.
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.