Calculate the TPS of the TITAN RTX on local AI models

NVIDIA 24 GB GDDR6 672 GB/s December 2018

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

532 models it can run

721 models in our catalogue altogether

Largest model it holds

Mixtral 8x7B

46.7B · Q3_K_M · 59.5 tok/s

Fastest model

Gemma 3 QAT 1B

285 tok/s · 1B

Which AI models can run on a TITAN RTX?

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.

532 models match

Calculating
Quantisation Fit
285 tok/s

242–342

Gemma 3 1B 1B Mar 2025 1.8 GB 33k tokens Q8_0 Comfortable
285 tok/s

242–342

Gemma 3 QAT 1B 1B Apr 2025 1.8 GB 33k tokens Q8_0 Comfortable
285 tok/s

171–455 · low confidence

HGRN 1B (WT 103) 1B Nov 2023 1.8 GB 131k tokens ? Q8_0 Comfortable
285 tok/s

171–455 · low confidence

LLama 3..2 Typhoon 2 1B 1B Dec 2024 1.8 GB 131k tokens ? Q8_0 Comfortable
285 tok/s

171–455 · low confidence

OLMo-1B 1B Feb 2024 1.8 GB 131k tokens ? Q8_0 Comfortable
285 tok/s

171–455 · low confidence

Pythia-1b 1B Apr 2023 1.8 GB 131k tokens ? Q8_0 Comfortable
264 tok/s

158–422 · low confidence

OpenELM-1.1B 1.1B May 2024 1.9 GB 131k tokens ? Q8_0 Comfortable
259 tok/s

155–414 · low confidence

DeciCoder-1B 1.1B Aug 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
259 tok/s

155–414 · low confidence

SantaCoder 1.1B Jan 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
259 tok/s

155–414 · low confidence

TinyLlama-1.1B (1T token checkpoint) 1.1B Oct 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
259 tok/s

155–414 · low confidence

TinyLlama-1.1B (3T token checkpoint) 1.1B Oct 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
237 tok/s

142–379 · low confidence

EXAONE 4.0 (1.2B) 1.2B Jul 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
237 tok/s

142–379 · low confidence

LFM2-1.2B 1.2B Jul 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
237 tok/s

142–379 · low confidence

MinerU2.5 1.2B Sep 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
237 tok/s

142–379 · low confidence

Pleias 1.0 1.2B 1.2B Dec 2024 2.0 GB 131k tokens ? Q8_0 Comfortable
237 tok/s

142–379 · low confidence

Pleias-RAG-1B 1.2B Apr 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
231 tok/s

197–278

Llama 3.2 1B 1.2B Sep 2024 2.2 GB 131k tokens Q8_0 Comfortable
228 tok/s

137–365 · low confidence

MiniCPM-1.2B 1.2B Jun 2024 2.0 GB 131k tokens ? Q8_0 Comfortable
219 tok/s

131–350 · low confidence

DeepSeek Coder 1.3B 1.3B Jan 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
219 tok/s

131–350 · low confidence

DeepSeek-VL-1.3B 1.3B Mar 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
219 tok/s

131–350 · low confidence

DigiRL 1.3B Jun 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
219 tok/s

131–350 · low confidence

GLA Transformer 1.3B 1.3B Aug 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
219 tok/s

131–350 · low confidence

Janus 1.3B 1.3B Oct 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
219 tok/s

131–350 · low confidence

Kosmos-2.5 1.3B Aug 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
219 tok/s

131–350 · low confidence

Otter 1.3B May 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

TITAN RTX 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
24 GB
Memory bandwidth
672 GB/s
Memory type
GDDR6
Memory bus width
384 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
TU102
Architecture
Turing
Generation
GeForce 20
Foundry
TSMC
Process size
12 nm
Transistors
18.6 billion
Transistor density
24,700 K/mm²
Die size
754 mm²
Released
18 December 2018

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
1.35 GHz
Boost clock
1.77 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
4,608
Texture mapping units
288
Render output units
96
Streaming multiprocessors
72
Tensor cores
576
Ray tracing cores
72
L1 cache
64 KB
L2 cache
6 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)
32.6 TFLOPS
Single precision (FP32)
16.3 TFLOPS
Double precision (FP64)
509.8 GFLOPS
Pixel rate
170 GPixel/s
Texture rate
510 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)
280 W
Suggested power supply
600 W
Power connectors
2x 8-pin
Bus interface
PCIe 3.0 x16
Slot width
Dual-slot
Dimensions
267 mm × 35 mm
Display outputs
1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C

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
7.5
DirectX
12.2
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
Shader model
6.8

Listings

Where to buy a TITAN RTX

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

Capacity and bandwidth

Memory

24 GB

Bandwidth

672 GB/s

Largest model

Mixtral 8x7B

TITAN RTX carries 24 GB of GDDR6. That covers the mid-sized models most people actually run. Once the runtime and driver reserve their working space, roughly this much is left: 21.6 GB.

Memory bandwidth reaches 672 GB/s across a bus of 384 bits. That is the number governing generation speed — arithmetic per byte read is small enough that the bus, not the cores, is what everything waits on.

That comes from a memory clock of 1.75 GHz. It is why core counts predict generation speed so poorly.

The practical ceiling is Mixtral 8x7B, 46.7B, compressed to Q3_K_M and generating around 59.5 tokens per second.

The chip and how it was built

TITAN RTX is built on the graphics processor TU102, using the architecture Turing from NVIDIA, as part of the generation GeForce 20.

The chip is manufactured by TSMC, on a process of 12 nm, with a die measuring 754 mm², holding 18.6 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 December 2018, roughly 7.7388771834986 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

32.6 TFLOPS

FP64

509.8 GFLOPS

Tensor cores

576

On paper TITAN RTX reaches 32.6 TFLOPS at half precision, and 16.3 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 reaches 509.8 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 576 tensor cores across 72 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 a base of 1.35 GHz to a boost of 1.77 GHz. 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

TITAN RTX has an L1 cache of 64 KB, backed by an L2 cache of 6 MB. 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 4,608 shading units, 288 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

280 W

TITAN RTX is rated at 280 W, and the suggested system power supply is 600 W. 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 dual-slot, measuring 267 mm long, and needs 2x 8-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 3.0 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 that run on a TITAN RTX

The biggest open-weight models that fit on this card, newest first. Each is shown at the best compression the card can hold.

  1. 01 Qwen3.6-35B-A3B 35B · Q4_K_M · Apr 2026 104 tok/s
  2. 02 Qwen3-Omni-30B-A3B 35.3B · Q4_K_M · Sep 2025 103 tok/s
  3. 03 Seed-OSS-36B-Base 36B · IQ4_XS · Aug 2025 19.4 tok/s
  4. 04 InternVL2_5-38B 38.4B · Q3_K_M · Dec 2024 20.0 tok/s
  5. 05 InternVL2-40B 40.1B · Q3_K_M · Jul 2024 19.2 tok/s
  6. 06 JIUTIAN-139MoE 38.8B · Q3_K_M · Jun 2024 19.8 tok/s
  7. 07 VILA1.5-40B 40B · Q3_K_M · May 2024 19.2 tok/s
  8. 08 Mixtral 8x7B 46.7B · Q3_K_M · Dec 2023 59.5 tok/s
  9. 09 Falcon-40B 40B · Q3_K_M · Mar 2023 19.2 tok/s
  10. 10 gpt-sw3-40b 40B · Q3_K_M · Mar 2023 19.2 tok/s

The fastest AI models on a TITAN RTX

Where this card produces tokens quickest. Smaller models dominate here, because generating each token means reading the whole model out of memory once.

  1. 01 Gemma 3 QAT 1B 1B · Q8_0 · 1.8 GB 285 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 285 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 285 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 285 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 285 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 285 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 264 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 259 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 259 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 259 tok/s

Step by step

How to work out the tokens per second of a TITAN RTX

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.

  1. 01

    Search for the model you want

    The table lists 532 models this card runs. Search narrows the list by name or by size.

  2. 02

    Set the context length you will actually use

    Drag the slider to the conversation length you plan to work at. The cache grows with the conversation, and against a card holding 24 GB that is frequently the difference between a model fitting and not.

  3. 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.

  4. 04

    Take the range as the answer

    The figures are calculated, not measured. The fastest result on this card is 285 tok/s on Gemma 3 QAT 1B. The same card and model vary by thirty to fifty per cent between inference runtimes.

  5. 05

    Check the memory column before committing

    Tight means it works today; comfortable means it still works when the conversation grows. Compare what each model needs against an available 24 GB.

  6. 06

    Open the model to compare cards

    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 right buy is TITAN RTX.

Answers

TITAN RTX — common questions

01

TITAN RTX— how much cache does it have?

The L1 cache is 64 KB, and the L2 cache is 6 MB. 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.

02

TITAN RTX— what are its TFLOPS?

It is rated at 32.6 TFLOPS at half precision and 16.3 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.

03

TITAN RTX— how many tensor cores does it have?

It has 576 tensor cores across 72 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.

04

TITAN RTX— does it support CUDA?

Yes. It reports CUDA compute capability 7.5. 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.

05

TITAN RTX— what bus interface does it use?

It uses PCIe 3.0 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.

06

TITAN RTX— is it good for running local AI models?

Its memory comfortably covers the mid-sized models most people run locally and its bandwidth gives usable, if unspectacular, generation speeds. In total it runs 532 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.

07

TITAN RTX— can it run a model that does not fit in its memory?

Only partly. Layers beyond the card's 24 GB sit in system memory and run at a fraction of the speed, so a mostly-offloaded model is rarely worth using. Every figure here assumes it is fully resident on the card.

08

Would two TITAN RTX cards be twice as fast?

Capacity adds, throughput does not. Two of them give you 48 GB of combined memory, at roughly the same generation speed as one.

09

TITAN RTX— which AI models can it run?

532 of the 721 open-weight language models we track fit on this card and can be run locally. The table on this page lists every one, with the memory it needs, the quantisation it runs at and an estimated generation speed.

10

TITAN RTX— what is the largest AI model it can run?

The largest model in our catalogue that fits is Mixtral 8x7B at 46.7B parameters, compressed to Q3_K_M. It generates roughly 59.5 tokens per second and needs about 21.0 GB of the card's memory.

11

TITAN RTX— how many tokens per second does it produce?

It depends on the model. The fastest model we track here is Gemma 3 QAT 1B at about 285 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.

12

TITAN RTX— can it run 7B models?

Yes. For example it runs Gemma 4 E4B at Q8_0, using about 9.8 GB of memory and generating around 63.3 tokens per second.

13

TITAN RTX— can it run 13B models?

Yes. For example it runs DeepSeekMoE-16B at Q8_0, using about 17.5 GB of memory and generating around 98.8 tokens per second.

14

TITAN RTX— can it run 30B models?

Yes. For example it runs Nemotron 3-Nano-30B-A3B at Q4_K_M, using about 18.1 GB of memory and generating around 116 tokens per second.

15

TITAN RTX— how much memory does it have?

This card has 24 GB of GDDR6. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 21.6 GB available for a model and its conversation.

16

TITAN RTX— what is its memory bandwidth?

Memory bandwidth reaches 672 GB/s across a bus of 384 bits. 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.

17

TITAN RTX— what type of memory does it use?

It uses GDDR6 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.

18

TITAN RTX— who makes it?

This is a product of NVIDIA, with the chip manufactured by TSMC, on a process of 12 nm.

19

TITAN RTX— when was it released?

It was released in December 2018.

20

TITAN RTX— how much power does it use?

Rated board power is 280 W, and the suggested system power supply is 600 W. Generating text draws hard in bursts and idles between requests, so average consumption over a working session is normally well below the rated figure.

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.

All GPUs