Calculate the TPS of the GeForce GTX TITAN Z on local AI models

NVIDIA 6 GB GDDR5 336 GB/s May 2014

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

266 models it can run

679 models in our catalogue altogether

Largest model it holds

Qwen-VL

9.6B · Q3_K_M · 34.0 tok/s

Fastest model

Gemma 3 QAT 1B

121 tok/s · 1B

Which AI models can run on a GeForce GTX TITAN Z?

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.

266 models match

Calculating
Quantisation Fit
121 tok/s

42–242 · low confidence

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

42–242 · low confidence

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

42–242 · low confidence

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

42–242 · low confidence

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

42–242 · low confidence

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

42–242 · low confidence

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

39–224 · low confidence

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

38–220 · low confidence

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

38–220 · low confidence

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

38–220 · low confidence

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

38–220 · low confidence

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

35–202 · low confidence

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

35–202 · low confidence

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

35–202 · low confidence

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

35–202 · low confidence

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

34–197 · low confidence

Llama 3.2 1B 1.2B Sep 2024 2.2 GB 113k tokens Q8_0 Comfortable
97.0 tok/s

34–194 · low confidence

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

33–186 · low confidence

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

33–186 · low confidence

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

33–186 · low confidence

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

33–186 · low confidence

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

33–186 · low confidence

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

33–186 · low confidence

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

33–186 · low confidence

Otter ≈ 1.3B May 2023 2.1 GB 131k tokens ? Q8_0 Comfortable
93.1 tok/s

33–186 · 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 GTX TITAN Z 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
6 GB
Memory bandwidth
336 GB/s
Memory type
GDDR5
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
GK110B
Architecture
Kepler
Generation
GeForce 700
Foundry
TSMC
Process size
28 nm
Transistors
7.1 billion
Transistor density
12,600 K/mm²
Die size
561 mm²
Package
BGA-2152
Released
28 May 2014

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
705 MHz
Boost clock
876 MHz

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
2,880
Texture mapping units
240
Render output units
48
L1 cache
16 KB
L2 cache
1.5 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.

Single precision (FP32)
5 TFLOPS
Double precision (FP64)
1.7 TFLOPS
Pixel rate
53 GPixel/s
Texture rate
210 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)
375 W
Suggested power supply
750 W
Power connectors
2x 8-pin
Bus interface
PCIe 3.0 x16
Slot width
Triple-slot
Dimensions
267 mm × 62 mm
Display outputs
2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2

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
3.5
DirectX
11.1
OpenGL
4.6
Vulkan
1.2
OpenCL
3.0
Shader model
5.1

Listings

Where to buy a GeForce GTX TITAN Z

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

6 GB

Bandwidth

336 GB/s

Largest model

Qwen-VL

At 6 GB of GDDR5 the GeForce GTX TITAN Z is limited to the smaller end of the catalogue. About 5.4 GB is actually available to a runtime, and a model has to fit entirely inside it before generating anything at all.

The memory bus moves 336 GB/s across a 384-bit bus. That is the number that governs generation speed — arithmetic per byte read is small enough that the bus, not the cores, is what everything waits on.

The figure is the memory clock — 1.75 GHz here — multiplied by the bus width. It is why core counts predict generation speed so poorly.

The practical ceiling is Qwen-VL at 9.6B, held at Q3_K_M and running at roughly 34.0 tokens per second.

The chip and how it was built

The GeForce GTX TITAN Z is built on the GK110B graphics processor, using NVIDIA's Kepler architecture, as part of the GeForce 700 generation.

The chip is manufactured by TSMC, on a 28 nm process, with a die measuring 561 mm², holding 7.1 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 May 2014, roughly 12 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

FP64

1.7 TFLOPS

Double-precision throughput is 1.7 TFLOPS. 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.

Clocks run from 705 MHz at base to 876 MHz 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 GTX TITAN Z has 16 KB of L1 cache, backed by 1.5 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 2,880 shading units, 240 texture mapping units, and 48 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

375 W

The GeForce GTX TITAN Z is rated at 375 W, with a 750 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 triple-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 GeForce GTX TITAN Z

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 Qwen3.5-9B 9B · Q3_K_M · Feb 2026 36.3 tok/s
  2. 02 NVIDIA-Nemotron-Nano-9B-v2 9B · Q3_K_M · Aug 2025 36.3 tok/s
  3. 03 Ovis2.5 9B 9B · Q3_K_M · Aug 2025 36.3 tok/s
  4. 04 GLM-4.1V-Thinking 9B · Q3_K_M · Aug 2025 36.3 tok/s
  5. 05 MamayLM 9B · Q3_K_M · Apr 2025 36.3 tok/s
  6. 06 GLM-4-9B-0414 9B · Q3_K_M · Apr 2025 36.3 tok/s
  7. 07 SimPO 9B · Q3_K_M · Nov 2024 36.3 tok/s
  8. 08 GLM-4V-9B 9B · Q3_K_M · Jun 2024 36.3 tok/s
  9. 09 Persimmon-8B 9.3B · Q3_K_M · Sep 2023 35.1 tok/s
  10. 10 Qwen-VL 9.6B · Q3_K_M · Aug 2023 34.0 tok/s

The fastest AI models on a GeForce GTX TITAN Z

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 121 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 121 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 121 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 121 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 121 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 121 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 112 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 110 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 110 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 110 tok/s

Step by step

How to work out the tokens per second of a GeForce GTX TITAN Z

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

    All 266 models the GeForce GTX TITAN Z handles are already listed. The search box takes a name or a size such as 27b, which matches on parameter count.

  2. 02

    Decide how long your conversations run

    Drag the slider to the conversation length you plan to work at. The cache grows with the conversation, and on 6 GB it is often what pushes a large model over the edge.

  3. 03

    Choose how far you will compress

    Each model is shown at the best compression this card can hold. A minimum quality hides the ones that only fit by being squeezed further than you would accept.

  4. 04

    Take the range as the answer

    The figures are calculated, not measured. 121 tok/s on Gemma 3 QAT 1B is the fastest result on this card, and like every row it carries a range that reflects how much the runtime matters.

  5. 05

    Check the memory column before committing

    Compare what each model needs with the 6 GB this card provides. Tight means it works today; comfortable means it still works when the conversation grows.

  6. 06

    Check the same model from the other side

    Each model page repeats this calculation for the whole catalogue. Worth a look before deciding: it shows what else runs the same model, and how the GeForce GTX TITAN Z compares.

Answers

GeForce GTX TITAN Z — common questions

01

How much power does a GeForce GTX TITAN Z use?

The GeForce GTX TITAN Z has a rated board power of 375 W, and a 750 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.

02

How much cache does a GeForce GTX TITAN Z have?

The GeForce GTX TITAN Z has 16 KB of L1 cache, and 1.5 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.

03

Does the GeForce GTX TITAN Z support CUDA?

Yes. The GeForce GTX TITAN Z reports CUDA compute capability 3.5, which predates tensor cores. 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.

04

What bus interface does the GeForce GTX TITAN Z 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.

05

Is the GeForce GTX TITAN Z good for running local AI models?

Its memory limits it to smaller models though its bandwidth means generation will feel slow on larger models. In total it runs 266 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.

06

Can a GeForce GTX TITAN Z run a model that does not fit in its memory?

Only partly. Layers beyond the 6 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.

07

Would two GeForce GTX TITAN Z cards be twice as fast?

No. A second GeForce GTX TITAN Z doubles the memory to 12 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.

08

What AI models can a GeForce GTX TITAN Z run?

266 of the 679 open-weight language models we track fit on a GeForce GTX TITAN Z 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.

09

What is the largest AI model a GeForce GTX TITAN Z can run?

The largest model in our catalogue that fits on a GeForce GTX TITAN Z is Qwen-VL at 9.6B parameters, compressed to Q3_K_M. It generates roughly 34.0 tokens per second and needs about 5.4 GB of the card's memory.

10

How many tokens per second does a GeForce GTX TITAN Z produce?

It depends on the model. On a GeForce GTX TITAN Z the fastest model we track is Gemma 3 QAT 1B at about 121 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.

11

Can a GeForce GTX TITAN Z run a 7B model?

Yes. For example a GeForce GTX TITAN Z runs MetaMath 7B (Mistral finetune) at IQ4_XS, using about 5.1 GB of memory and generating around 42.4 tokens per second.

12

How much memory does a GeForce GTX TITAN Z have?

A GeForce GTX TITAN Z has 6 GB of GDDR5 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 5.4 GB available for a model and its conversation.

13

What is the memory bandwidth of a GeForce GTX TITAN Z?

The GeForce GTX TITAN Z has 336 GB/s of memory bandwidth, across a 384-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.

14

What type of memory does a GeForce GTX TITAN Z use?

It uses GDDR5 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.

15

Who makes the GeForce GTX TITAN Z?

The GeForce GTX TITAN Z is a NVIDIA product, with the chip manufactured by TSMC, on a 28 nm process.

16

When was the GeForce GTX TITAN Z released?

The GeForce GTX TITAN Z was released in May 2014.

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