Calculate the TPS of the GeForce GTX 980 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
679 models in our catalogue altogether
Largest model it holds
Qwen-VL
9.6B · Q3_K_M · 34.1 tok/s
Fastest model
Gemma 3 QAT 1B
121 tok/s · 1B
Which AI models can run on a GeForce GTX 980 Ti?
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
39–220 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
39–220 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
39–220 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
39–220 · 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 |
|
98.5
tok/s
34–197 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 113k tokens | Q8_0 | Comfortable |
|
97.1
tok/s
34–194 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.2
tok/s
33–186 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.2
tok/s
33–186 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.2
tok/s
33–186 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.2
tok/s
33–186 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.2
tok/s
33–186 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.2
tok/s
33–186 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.2
tok/s
33–186 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.2
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 980 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
- 6 GB
- Memory bandwidth
- 337 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
- GM200
- Architecture
- Maxwell 2.0
- Generation
- GeForce 900
- Foundry
- TSMC
- Process size
- 28 nm
- Transistors
- 8 billion
- Transistor density
- 13,300 K/mm²
- Die size
- 601 mm²
- Package
- BGA-2152
- Released
- 2 June 2015
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 GHz
- Boost clock
- 1.08 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
- 2,816
- Texture mapping units
- 176
- Render output units
- 96
- Streaming multiprocessors
- 22
- L1 cache
- 48 KB
- L2 cache
- 3 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)
- 6.1 TFLOPS
- Double precision (FP64)
- 189.4 GFLOPS
- Pixel rate
- 103 GPixel/s
- Texture rate
- 189 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 DVI, 1x HDMI 2.0, 3x 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
- 5.2
- DirectX
- 12.1
- OpenGL
- 4.6
- Vulkan
- 1.4
- OpenCL
- 3.0
- Shader model
- 6.8
Listings
Where to buy a GeForce GTX 980 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
6 GB
Bandwidth
337 GB/s
Largest model
Qwen-VL
At 6 GB of GDDR5 the GeForce GTX 980 Ti 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 337 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.
Put together, the largest model that fits is Qwen-VL at 9.6B, running Q3_K_M and producing around 34.1 tokens per second.
The chip and how it was built
The GeForce GTX 980 Ti is built on the GM200 graphics processor, using NVIDIA's Maxwell 2.0 architecture, as part of the GeForce 900 generation.
The chip is manufactured by TSMC, on a 28 nm process, with a die measuring 601 mm², holding 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 June 2015, roughly 11 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
189.4 GFLOPS
Double-precision throughput is 189.4 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 GHz at base to 1.08 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 980 Ti has 48 KB of L1 cache, backed by 3 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 2,816 shading units, 176 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
250 W
The GeForce GTX 980 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 that run on a GeForce GTX 980 Ti
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 GTX 980 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 GTX 980 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
Search for the model you want
All 266 models the GeForce GTX 980 Ti handles are already listed. The search box takes a name or a size such as 27b, which matches on parameter count.
-
02
Match the context to your work
Longer conversations cost memory on top of the weights. With 6 GB to work in, that is frequently the difference between a model fitting and not.
-
03
Choose how far you will compress
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
Look at the range, not just the number
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.
-
05
Read the fit verdict last
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.
-
06
Check the same model from the other side
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 GTX 980 Ti is the right buy for it or merely a card that fits.
Answers
GeForce GTX 980 Ti — common questions
Would two GeForce GTX 980 Ti cards be twice as fast?
No. A second GeForce GTX 980 Ti 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.
What AI models can a GeForce GTX 980 Ti run?
266 of the 679 open-weight language models we track fit on a GeForce GTX 980 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 GTX 980 Ti can run?
The largest model in our catalogue that fits on a GeForce GTX 980 Ti is Qwen-VL at 9.6B parameters, compressed to Q3_K_M. It generates roughly 34.1 tokens per second and needs about 5.4 GB of the card's memory.
How many tokens per second does a GeForce GTX 980 Ti produce?
It depends on the model. On a GeForce GTX 980 Ti 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.
Can a GeForce GTX 980 Ti run a 7B model?
Yes. For example a GeForce GTX 980 Ti runs MetaMath 7B (Mistral finetune) at IQ4_XS, using about 5.1 GB of memory and generating around 42.5 tokens per second.
How much memory does a GeForce GTX 980 Ti have?
A GeForce GTX 980 Ti 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.
What is the memory bandwidth of a GeForce GTX 980 Ti?
The GeForce GTX 980 Ti has 337 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.
What type of memory does a GeForce GTX 980 Ti 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.
Who makes the GeForce GTX 980 Ti?
The GeForce GTX 980 Ti is a NVIDIA product, with the chip manufactured by TSMC, on a 28 nm process.
When was the GeForce GTX 980 Ti released?
The GeForce GTX 980 Ti was released in June 2015.
How much power does a GeForce GTX 980 Ti use?
The GeForce GTX 980 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.
How much cache does a GeForce GTX 980 Ti have?
The GeForce GTX 980 Ti has 48 KB of L1 cache, and 3 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.
Does the GeForce GTX 980 Ti support CUDA?
Yes. The GeForce GTX 980 Ti reports CUDA compute capability 5.2, 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.
What bus interface does the GeForce GTX 980 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.
Is the GeForce GTX 980 Ti 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.
Can a GeForce GTX 980 Ti run a model that does not fit in its memory?
Offloading past the card's 6 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.
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.