Calculate the TPS of the GeForce GTX 1080 Ti on local AI models

NVIDIA 11 GB GDDR5X 484 GB/s March 2017

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

389 of 679 models it can run

Largest model it holds

GigaChat Lite (GigaChat-20B-A3B)

20B · Q3_K_M · 131 tok/s

Fastest model

Gemma 3 QAT 1B

174 tok/s · 1B

What AI models can a GeForce GTX 1080 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.

389 models match

Calculating
Quantisation Fit
174 tok/s

61–349 · low confidence

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

61–349 · low confidence

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

61–349 · low confidence

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

61–349 · low confidence

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

61–349 · low confidence

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

61–349 · low confidence

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

57–323 · low confidence

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

55–317 · low confidence

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

55–317 · low confidence

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

55–317 · low confidence

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

55–317 · low confidence

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

52–297 · low confidence

DeepSeekMoE-16B 16B Jan 2024 9.1 GB 4k tokens IQ4_XS Tight
145 tok/s

51–291 · low confidence

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

51–291 · low confidence

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

51–291 · low confidence

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

51–291 · low confidence

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

50–284 · low confidence

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

49–280 · low confidence

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

47–268 · low confidence

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

47–268 · low confidence

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

47–268 · low confidence

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

47–268 · low confidence

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

47–268 · low confidence

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

47–268 · low confidence

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

47–268 · 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

GeForce GTX 1080 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
11 GB
Memory bandwidth
484 GB/s
Memory type
GDDR5X
Memory bus width
352 bit
Memory clock
1.38 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
GP102
Architecture
Pascal
Generation
GeForce 10
Foundry
TSMC
Process size
16 nm
Transistors
11.8 billion
Transistor density
25,100 K/mm²
Die size
471 mm²
Package
BGA-2397
Released
10 March 2017

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
1.48 GHz
Boost clock
1.58 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
3,584
Texture mapping units
224
Render output units
88
Streaming multiprocessors
28
L1 cache
48 KB
L2 cache
2.75 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)
177.2 GFLOPS
Single precision (FP32)
11.3 TFLOPS
Double precision (FP64)
354.4 GFLOPS
Pixel rate
139 GPixel/s
Texture rate
354 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)
250 W
Suggested power supply
600 W
Power connectors
1x 6-pin + 1x 8-pin
Bus interface
PCIe 3.0 x16
Slot width
Dual-slot
Dimensions
267 mm × 40 mm
Display outputs
1x HDMI 2.0, 3x DisplayPort 1.4a

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
6.1
DirectX
12.1
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
Shader model
6.8

Listings

Where to buy a GeForce GTX 1080 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

Why memory is the number that matters here

Memory

11 GB

Bandwidth

484 GB/s

Largest model

GigaChat Lite (GigaChat-20B-A3B)

At 11 GB of GDDR5X the GeForce GTX 1080 Ti is limited to the smaller end of the catalogue. About 9.9 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 484 GB/s across a 352-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 — 1.38 GHz here — multiplied by the bus width. It is why core counts predict generation speed so poorly.

The practical ceiling is GigaChat Lite (GigaChat-20B-A3B) at 20B, held at Q3_K_M and running at roughly 131 tokens per second.

The chip and how it was built

The GeForce GTX 1080 Ti is built on the GP102 graphics processor, using NVIDIA's Pascal architecture, as part of the GeForce 10 generation.

The chip is manufactured by TSMC, on a 16 nm process, with a die measuring 471 mm², holding 11.8 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 March 2017, roughly 9 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

177.2 GFLOPS

FP64

354.4 GFLOPS

On paper the GeForce GTX 1080 Ti reaches 177.2 GFLOPS at half precision and 11.3 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 is 354.4 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.

Clocks run from 1.48 GHz at base to 1.58 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 GTX 1080 Ti has 48 KB of L1 cache, backed by 2.75 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 3,584 shading units, 224 texture mapping units, and 88 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

250 W

The GeForce GTX 1080 Ti is rated at 250 W, with a 600 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 267 mm long, and needs 1x 6-pin + 1x 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 a GeForce GTX 1080 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.

  1. 01 Ring-mini-linear-2.0 16.4B · IQ4_XS · Oct 2025 26.1 tok/s
  2. 02 Ling-mini-base-2.0-20T 16B · IQ4_XS · Sep 2025 26.8 tok/s
  3. 03 Ling-lite-1.5 ("Bailing") 16.8B · IQ4_XS · Mar 2025 25.5 tok/s
  4. 04 GigaChat Lite (GigaChat-20B-A3B) 20B · Q3_K_M · Dec 2024 131 tok/s
  5. 05 DeepSeekMoE-16B 16B · IQ4_XS · Jan 2024 149 tok/s
  6. 06 CogAgent 18B · Q3_K_M · Dec 2023 26.1 tok/s
  7. 07 CogVLM-17B 17B · Q3_K_M · Nov 2023 27.7 tok/s
  8. 08 Nanbeige-16B 16B · IQ4_XS · Nov 2023 26.8 tok/s
  9. 09 CodeT5+ 16B · IQ4_XS · May 2023 26.8 tok/s
  10. 10 CodeGen-Mono 16.1B 16.1B · IQ4_XS · Feb 2023 26.6 tok/s

The fastest AI models on a GeForce GTX 1080 Ti

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 174 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 174 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 174 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 174 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 174 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 174 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 161 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 159 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 159 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 159 tok/s

Step by step

How to work out the tokens per second of a GeForce GTX 1080 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.

  1. 01

    Start with the model, not the specification

    The table lists 389 models this GeForce GTX 1080 Ti can run. Search by name, or by size — typing 27b matches on the parameter count even when the name never states it.

  2. 02

    Decide how long your conversations run

    Set the context to your real working length. Short questions cost almost nothing; a long document can consume a large share of the card's 11 GB.

  3. 03

    Pin the comparison to one quality level

    By default the table picks the least-compressed copy that fits. Setting a floor removes models that only qualify through heavy compression.

  4. 04

    Look at the range, not just the number

    Speeds come with error bars for a reason. The best case here is 174 tok/s on Gemma 3 QAT 1B, and which inference software you use moves that by thirty to fifty per cent.

  5. 05

    Check the headroom before you decide

    A tight fit runs but leaves no room to raise the context later; comfortable has headroom. The memory column shows what each model needs against the 11 GB available.

  6. 06

    Check the same model from the other side

    Following a model through to its own page lists all the hardware that can run it, so you can see where the GeForce GTX 1080 Ti sits against the alternatives.

Answers

GeForce GTX 1080 Ti — common questions

01

What is the largest AI model a GeForce GTX 1080 Ti can run?

The largest model in our catalogue that fits on a GeForce GTX 1080 Ti is GigaChat Lite (GigaChat-20B-A3B) at 20B parameters, compressed to Q3_K_M. It generates roughly 131 tokens per second and needs about 9.7 GB of the card's memory.

02

How many tokens per second does a GeForce GTX 1080 Ti produce?

It depends on the model. On a GeForce GTX 1080 Ti the fastest model we track is Gemma 3 QAT 1B at about 174 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.

03

Can a GeForce GTX 1080 Ti run a 7B model?

Yes. For example a GeForce GTX 1080 Ti runs Qwen1.5-7B at Q5_K_M, using about 9.3 GB of memory and generating around 44.5 tokens per second.

04

Can a GeForce GTX 1080 Ti run a 13B model?

Yes. For example a GeForce GTX 1080 Ti runs DeepSeekMoE-16B at IQ4_XS, using about 9.1 GB of memory and generating around 149 tokens per second.

05

How much memory does a GeForce GTX 1080 Ti have?

A GeForce GTX 1080 Ti has 11 GB of GDDR5X memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 9.9 GB available for a model and its conversation.

06

What is the memory bandwidth of a GeForce GTX 1080 Ti?

The GeForce GTX 1080 Ti has 484 GB/s of memory bandwidth, across a 352-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.

07

What type of memory does a GeForce GTX 1080 Ti use?

It uses GDDR5X clocked at 1.38 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.

08

Who makes the GeForce GTX 1080 Ti?

The GeForce GTX 1080 Ti is a NVIDIA product, with the chip manufactured by TSMC, on a 16 nm process.

09

When was the GeForce GTX 1080 Ti released?

The GeForce GTX 1080 Ti was released in March 2017.

10

How much power does a GeForce GTX 1080 Ti use?

The GeForce GTX 1080 Ti has a rated board power of 250 W, and a 600 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.

11

How much cache does a GeForce GTX 1080 Ti have?

The GeForce GTX 1080 Ti has 48 KB of L1 cache, and 2.75 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.

12

What are the TFLOPS of a GeForce GTX 1080 Ti?

The GeForce GTX 1080 Ti is rated at 177.2 GFLOPS at half precision and 11.3 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.

13

Does the GeForce GTX 1080 Ti support CUDA?

Yes. The GeForce GTX 1080 Ti reports CUDA compute capability 6.1, 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.

14

What bus interface does the GeForce GTX 1080 Ti 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.

15

Is the GeForce GTX 1080 Ti good for running local AI models?

Its memory limits it to smaller models and its bandwidth gives usable, if unspectacular, generation speeds. In total it runs 389 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.

16

Can a GeForce GTX 1080 Ti run a model that does not fit in its memory?

Offloading past the card's 11 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.

17

Would two GeForce GTX 1080 Ti cards be twice as fast?

Pairing GeForce GTX 1080 Ti cards buys headroom rather than pace: 22 GB of combined memory, at roughly the same generation speed as one.

18

What AI models can a GeForce GTX 1080 Ti run?

389 of the 679 open-weight language models we track fit on a GeForce GTX 1080 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.

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