Calculate the TPS of the GeForce RTX 5070 Ti on local AI models
Every model in our catalogue assessed against this card at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from this card's memory bandwidth and the size of each model once compressed.
Calculated for this card
Largest model it holds
Nemotron 3-Nano-30B-A3B
31.6B · Q3_K_M · 180 tok/s
Fastest model
Gemma 3 QAT 1B
379 tok/s · 1B
What AI models can a GeForce RTX 5070 Ti run?
Set the inputs, read the answer
More context means more memory for the conversation cache. Speed is for a fresh conversation and does not change with this setting.
Hides models that would only fit by being compressed below this point.
432 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
379
tok/s
323–455 |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
379
tok/s
323–455 |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
379
tok/s
228–607 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
379
tok/s
228–607 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
379
tok/s
228–607 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
379
tok/s
228–607 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
351
tok/s
211–562 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
345
tok/s
207–552 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
345
tok/s
207–552 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
345
tok/s
207–552 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
345
tok/s
207–552 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
316
tok/s
190–506 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
316
tok/s
190–506 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
316
tok/s
190–506 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
316
tok/s
190–506 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
309
tok/s
262–370 |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
304
tok/s
183–487 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
292
tok/s
175–467 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
292
tok/s
175–467 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
292
tok/s
175–467 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
292
tok/s
175–467 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
292
tok/s
175–467 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
292
tok/s
175–467 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
292
tok/s
175–467 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
292
tok/s
175–467 · low confidence |
Phi-1 ≈ | 1.3B | Oct 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
Speeds are estimates for a single request — one conversation at a time — calculated from memory bandwidth, model size and quantisation. Real throughput varies with the inference runtime and its version. Figures published by hardware vendors measure many simultaneous requests and are much higher.
On record
GeForce RTX 5070 Ti full specification
Everything on record for this board, ordered by how much it bears on running a language model rather than by how a spec sheet would list it. Memory comes first because it decides the outcome; the rest is context.
Memory
The two specifications that decide what this card can run and how quickly. Capacity sets which models fit; bandwidth sets how many tokens per second they produce once they do.
- Memory size
- 16 GB
- Memory bandwidth
- 896 GB/s
- Memory type
- GDDR7
- Memory bus width
- 256 bit
- Memory clock
- 1.75 GHz
The chip
Which processor is on the board and how it was manufactured. A smaller process size generally means more performance for the same power.
- Graphics processor
- GB203
- Architecture
- Blackwell 2.0
- Generation
- GeForce 50
- Foundry
- TSMC
- Process size
- 5 nm
- Transistors
- 45.6 billion
- Transistor density
- 120,600 K/mm²
- Die size
- 378 mm²
- Released
- 20 February 2025
Clock speeds
How fast the processor runs. Worth far less here than on a gaming benchmark: generating text is limited by memory bandwidth, so a higher clock barely moves the result.
- Base clock
- 2.3 GHz
- Boost clock
- 2.45 GHz
Processing units
What the chip contains. These drive graphics performance and matter mainly for processing a long prompt rather than for producing the answer.
- Shading units
- 8,960
- Texture mapping units
- 280
- Render output units
- 96
- Streaming multiprocessors
- 70
- Tensor cores
- 280
- Ray tracing cores
- 70
- L1 cache
- 128 KB
- L2 cache
- 48 MB
Theoretical performance
Peak arithmetic rates published for the board. These are ceilings that no real workload reaches, and generating text reaches a small fraction of them because it is limited by memory rather than arithmetic.
- Half precision (FP16)
- 43.9 TFLOPS
- Single precision (FP32)
- 43.9 TFLOPS
- Double precision (FP64)
- 686.6 GFLOPS
- Pixel rate
- 235 GPixel/s
- Texture rate
- 687 GTexel/s
The board
What it takes to physically install and power the card — the practical constraints that decide whether it fits the machine you already own.
- Power draw (TDP)
- 300 W
- Suggested power supply
- 700 W
- Power connectors
- 1x 16-pin
- Bus interface
- PCIe 5.0 x16
- Slot width
- Dual-slot
- Dimensions
- 304 mm × 48 mm
- Display outputs
- 1x HDMI 2.1b, 3x DisplayPort 2.1b
Software support
Which graphics and compute interfaces the card supports. CUDA compute capability is the one that bears on inference: below 7.0 there are no tensor cores, and modern inference software falls back to slower code paths.
- CUDA compute capability
- 12.0
- DirectX
- 12.2
- OpenGL
- 4.6
- Vulkan
- 1.4
- OpenCL
- 3.0
- Shader model
- 6.8
Listings
Where to buy a GeForce RTX 5070 Ti
No vendor is currently listing this card. Listings come from vendors who publish them here directly — browse the vendor directory to see who is selling what.
What the numbers mean
What the memory subsystem means for AI
Memory
16 GB
Bandwidth
896 GB/s
Largest model
Nemotron 3-Nano-30B-A3B
16 GB of GDDR7 puts the GeForce RTX 5070 Ti comfortably into small and mid-sized models, with roughly 14.4 GB usable once the driver overhead is taken out. The largest models are out of reach without splitting them.
Bandwidth is 896 GB/s across a 256-bit bus. Generating a token means reading every weight once, so that figure sets the pace more than any other number here, and at this level text arrives faster than most people read.
That comes from a 1.75 GHz memory clock across the bus width above. Widening the bus and raising the clock are the two levers a manufacturer has, which is why a card with unremarkable cores can still generate quickly.
The biggest thing it holds is Nemotron 3-Nano-30B-A3B (31.6B) at Q3_K_M compression, for about 180 tokens per second.
The chip and how it was built
The GeForce RTX 5070 Ti is built on the GB203 graphics processor, using NVIDIA's Blackwell 2.0 architecture, as part of the GeForce 50 generation.
The chip is manufactured by TSMC, on a 5 nm process, with a die measuring 378 mm², holding 45.6 billion transistors. A smaller process generally means more performance for the same power, though for language models it matters far less than the memory subsystem.
It was released in February 2025, roughly 1 years ago. Inference software support tends to follow hardware by a year or two, so a card of this age generally has mature, well-optimised code paths available to it.
Compute throughput, and why it matters less than it looks
FP16
43.9 TFLOPS
FP64
686.6 GFLOPS
Tensor cores
280
On paper the GeForce RTX 5070 Ti reaches 43.9 TFLOPS at half precision and 43.9 TFLOPS at single precision. These are peak figures no real workload sustains, and generating text reaches only a small fraction of them — decoding is limited by memory rather than arithmetic, which is why a card can look enormously powerful here and still produce tokens at an ordinary rate.
Double-precision throughput is 686.6 GFLOPS. It has no bearing on running a language model — no inference runtime uses it — but it separates datacentre parts from consumer ones, since the latter deliberately restrict it.
The card carries 280 tensor cores across 70 streaming multiprocessors. These accelerate the matrix arithmetic at the heart of a transformer, and they are what make prompt processing — reading a long document before answering — dramatically faster than it would otherwise be.
Clocks run from 2.3 GHz at base to 2.45 GHz boosted. Worth far less here than on a gaming benchmark: raising the clock speeds up the arithmetic, and the arithmetic is not what generation is waiting on.
Cache and processing units
The GeForce RTX 5070 Ti has 128 KB of L1 cache, backed by 48 MB of L2. Cache absorbs a share of the memory traffic that would otherwise hit the main bus, which is the one place on this page where a number other than bandwidth quietly affects generation speed — a large L2 lets more of the working set stay close to the cores.
There are 8,960 shading units, 280 texture mapping units, and 96 render output units. These drive graphics workloads and contribute to prompt processing, but they sit idle for much of the time a model spends generating a reply.
Power, size and installation
Power draw
300 W
The GeForce RTX 5070 Ti is rated at 300 W, with a 700 W power supply suggested for the whole system. Running a language model keeps a card busy in bursts rather than continuously — it draws hard while generating and idles between requests — so sustained draw over a working day is usually well below the rated figure.
The board occupies a dual-slot, measuring 304 mm long, and needs 1x 16-pin. Worth checking against the case and power supply already in the machine, since the largest cards need considerably more of both than a typical desktop provides.
It connects over PCIe 5.0 x16. The interface governs how quickly a model is loaded from disk into the card, not how fast it runs once there, so a narrower link costs a few seconds at startup and nothing thereafter.
The extremes
The largest AI models a GeForce RTX 5070 Ti can run
The biggest open-weight models that fit on this card, newest first. Each is shown at the best compression the card can hold.
The fastest AI models on a GeForce RTX 5070 Ti
Where this card produces tokens quickest. Smaller models dominate here, because generating each token means reading the whole model out of memory once.
Step by step
How to work out the tokens per second of a GeForce RTX 5070 Ti
You do not have to calculate anything by hand — the gputps.com calculator on this page has already worked it out for every model this card can hold. Reading off the answer takes six steps.
-
01
Find the model in the table
The table lists 432 models this GeForce RTX 5070 Ti can run. Search by name, or by size — typing 27b matches on the parameter count even when the name never states it.
-
02
Match the context to your work
Longer conversations cost memory on top of the weights. With 16 GB to work in, that is frequently the difference between a model fitting and not.
-
03
Set a minimum quality if you need one
Compression is what lets bigger models fit. The quality control drops any model that needs more of it than you are willing to give.
-
04
Take the range as the answer
Each speed is an estimate for a single conversation, with a range beneath it — 379 tok/s on Gemma 3 QAT 1B at the top end here. The same card and model vary by thirty to fifty per cent between inference runtimes.
-
05
Check the headroom before you decide
The fit column separates models that just fit from those with room to spare — worth checking against the card's 16 GB before settling on one.
-
06
Cross-check against other hardware
Every model name in the table links to its own page, which runs the same calculation across every card we hold. That is where you see whether the GeForce RTX 5070 Ti is the right buy for it or merely a card that fits.
Answers
GeForce RTX 5070 Ti — common questions
What are the TFLOPS of a GeForce RTX 5070 Ti?
The GeForce RTX 5070 Ti is rated at 43.9 TFLOPS at half precision and 43.9 TFLOPS at single precision. These are peak arithmetic ceilings rather than achievable rates, and text generation reaches only a small fraction of them because it is limited by memory bandwidth instead.
How many tensor cores does a GeForce RTX 5070 Ti have?
The GeForce RTX 5070 Ti has 280 tensor cores across 70 streaming multiprocessors. They accelerate the matrix arithmetic a transformer is built from, which mainly speeds up processing a long prompt rather than producing the reply.
Does the GeForce RTX 5070 Ti support CUDA?
Yes. The GeForce RTX 5070 Ti reports CUDA compute capability 12.0. Capability 7.0 and above has tensor cores, which modern inference software uses; below that it falls back to slower code paths for quantised models.
What bus interface does the GeForce RTX 5070 Ti use?
It uses PCIe 5.0 x16. This governs how fast a model is loaded onto the card rather than how fast it runs once loaded, so it costs a few seconds at startup and nothing during generation.
Is the GeForce RTX 5070 Ti good for running local AI models?
Its memory covers small and mid-sized models, though the largest are out of reach and its bandwidth is high enough to generate text faster than most people read. In total it runs 432 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Can a GeForce RTX 5070 Ti run a model that does not fit in its memory?
Offloading past the card's 16 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.
Would two GeForce RTX 5070 Ti cards be twice as fast?
No. A second GeForce RTX 5070 Ti doubles the memory to 32 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.
What AI models can a GeForce RTX 5070 Ti run?
432 of the 679 open-weight language models we track fit on a GeForce RTX 5070 Ti and can be run locally on it. The table on this page lists every one, with the memory it needs, the quantisation it runs at and an estimated generation speed.
What is the largest AI model a GeForce RTX 5070 Ti can run?
The largest model in our catalogue that fits on a GeForce RTX 5070 Ti is Nemotron 3-Nano-30B-A3B at 31.6B parameters, compressed to Q3_K_M. It generates roughly 180 tokens per second and needs about 14.4 GB of the card's memory.
How many tokens per second does a GeForce RTX 5070 Ti produce?
It depends on the model. On a GeForce RTX 5070 Ti the fastest model we track is Gemma 3 QAT 1B at about 379 tokens per second, while larger models run proportionally slower because each token requires reading the whole model out of memory once. Speeds are estimates for a single conversation at a time.
Can a GeForce RTX 5070 Ti run a 7B model?
Yes. For example a GeForce RTX 5070 Ti runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 56.6 tokens per second.
Can a GeForce RTX 5070 Ti run a 13B model?
Yes. For example a GeForce RTX 5070 Ti runs DeepSeekMoE-16B at Q6_K, using about 13.7 GB of memory and generating around 191 tokens per second.
Can a GeForce RTX 5070 Ti run a 30B model?
Yes. For example a GeForce RTX 5070 Ti runs ERNIE-4.5-VL-28B-A3B at Q3_K_M, using about 12.9 GB of memory and generating around 203 tokens per second.
How much memory does a GeForce RTX 5070 Ti have?
A GeForce RTX 5070 Ti has 16 GB of GDDR7 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 14.4 GB available for a model and its conversation.
What is the memory bandwidth of a GeForce RTX 5070 Ti?
The GeForce RTX 5070 Ti has 896 GB/s of memory bandwidth, across a 256-bit memory bus. This is the single best predictor of how fast it generates text, because producing each token means reading the entire model out of memory once.
What type of memory does a GeForce RTX 5070 Ti use?
It uses GDDR7 clocked at 1.75 GHz. HBM types are found on datacentre accelerators and carry far more bandwidth than the GDDR used on desktop cards, which is why they generate tokens considerably faster at the same capacity.
Who makes the GeForce RTX 5070 Ti?
The GeForce RTX 5070 Ti is a NVIDIA product, with the chip manufactured by TSMC, on a 5 nm process.
When was the GeForce RTX 5070 Ti released?
The GeForce RTX 5070 Ti was released in February 2025.
How much power does a GeForce RTX 5070 Ti use?
The GeForce RTX 5070 Ti has a rated board power of 300 W, and a 700 W system power supply is suggested. Generating text draws hard in bursts and idles between requests, so average consumption over a working session is normally well below the rated figure.
How much cache does a GeForce RTX 5070 Ti have?
The GeForce RTX 5070 Ti has 128 KB of L1 cache, and 48 MB of L2 cache. Cache absorbs part of the memory traffic that would otherwise reach the main bus, so a larger L2 gives a modest lift to generation speed beyond what bandwidth alone predicts.
The other direction
Looking at it from the other side?
This page starts from the hardware. If you already know which model you want and need to know what it takes to run it, start from the model instead.