Calculate the TPS of the GeForce RTX 5080 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 · 193 tok/s
Fastest model
Gemma 3 QAT 1B
407 tok/s · 1B
What AI models can a GeForce RTX 5080 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 | ||||||
|---|---|---|---|---|---|---|---|
|
407
tok/s
346–488 |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
407
tok/s
346–488 |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
407
tok/s
244–651 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
407
tok/s
244–651 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
407
tok/s
244–651 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
407
tok/s
244–651 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
376
tok/s
226–602 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
370
tok/s
222–591 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
370
tok/s
222–591 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
370
tok/s
222–591 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
370
tok/s
222–591 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
339
tok/s
203–542 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
339
tok/s
203–542 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
339
tok/s
203–542 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
339
tok/s
203–542 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
331
tok/s
281–397 |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
326
tok/s
196–522 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
313
tok/s
188–500 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
313
tok/s
188–500 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
313
tok/s
188–500 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
313
tok/s
188–500 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
313
tok/s
188–500 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
313
tok/s
188–500 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
313
tok/s
188–500 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
313
tok/s
188–500 · 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 5080 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
- 960 GB/s
- Memory type
- GDDR7
- Memory bus width
- 256 bit
- Memory clock
- 1.88 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
- 30 January 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
- 2.62 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
- 10,752
- Texture mapping units
- 336
- Render output units
- 112
- Streaming multiprocessors
- 84
- Tensor cores
- 336
- Ray tracing cores
- 84
- L1 cache
- 128 KB
- L2 cache
- 64 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)
- 56.3 TFLOPS
- Single precision (FP32)
- 56.3 TFLOPS
- Double precision (FP64)
- 879.3 GFLOPS
- Pixel rate
- 293 GPixel/s
- Texture rate
- 879 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)
- 360 W
- Suggested power supply
- 750 W
- Power connectors
- 1x 16-pin
- Bus interface
- PCIe 5.0 x16
- Slot width
- Dual-slot
- Dimensions
- 304 mm × 40 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 5080
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
Memory: the specification that decides everything
Memory
16 GB
Bandwidth
960 GB/s
Largest model
Nemotron 3-Nano-30B-A3B
16 GB of GDDR7 puts the GeForce RTX 5080 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 960 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 1.88 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.
In practice that combination tops out at Nemotron 3-Nano-30B-A3B — 31.6B, compressed to Q3_K_M, generating around 193 tokens per second.
The chip and how it was built
The GeForce RTX 5080 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 January 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
56.3 TFLOPS
FP64
879.3 GFLOPS
Tensor cores
336
On paper the GeForce RTX 5080 reaches 56.3 TFLOPS at half precision and 56.3 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 879.3 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 336 tensor cores across 84 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 2.62 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 5080 has 128 KB of L1 cache, backed by 64 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 10,752 shading units, 336 texture mapping units, and 112 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
360 W
The GeForce RTX 5080 is rated at 360 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 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 5080 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 5080
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 5080
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 5080 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
Pin the comparison to one quality level
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.
-
04
Read the speed and the range
The figures are calculated, not measured. 407 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
Check the headroom before you decide
Compare what each model needs with the 16 GB this card provides. Tight means it works today; comfortable means it still works when the conversation grows.
-
06
Open the model to compare cards
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 RTX 5080 compares.
Answers
GeForce RTX 5080 — common questions
When was the GeForce RTX 5080 released?
The GeForce RTX 5080 was released in January 2025.
How much power does a GeForce RTX 5080 use?
The GeForce RTX 5080 has a rated board power of 360 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.
How much cache does a GeForce RTX 5080 have?
The GeForce RTX 5080 has 128 KB of L1 cache, and 64 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.
What are the TFLOPS of a GeForce RTX 5080?
The GeForce RTX 5080 is rated at 56.3 TFLOPS at half precision and 56.3 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.
How many tensor cores does a GeForce RTX 5080 have?
The GeForce RTX 5080 has 336 tensor cores across 84 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 5080 support CUDA?
Yes. The GeForce RTX 5080 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 5080 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 5080 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 5080 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 5080 cards be twice as fast?
Capacity adds, throughput does not. Two of them give you 32 GB to work with rather than twice the tokens per second — every figure here is for a single GeForce RTX 5080.
What AI models can a GeForce RTX 5080 run?
432 of the 679 open-weight language models we track fit on a GeForce RTX 5080 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 5080 can run?
The largest model in our catalogue that fits on a GeForce RTX 5080 is Nemotron 3-Nano-30B-A3B at 31.6B parameters, compressed to Q3_K_M. It generates roughly 193 tokens per second and needs about 14.4 GB of the card's memory.
How many tokens per second does a GeForce RTX 5080 produce?
It depends on the model. On a GeForce RTX 5080 the fastest model we track is Gemma 3 QAT 1B at about 407 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 5080 run a 7B model?
Yes. For example a GeForce RTX 5080 runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 60.7 tokens per second.
Can a GeForce RTX 5080 run a 13B model?
Yes. For example a GeForce RTX 5080 runs DeepSeekMoE-16B at Q6_K, using about 13.7 GB of memory and generating around 205 tokens per second.
Can a GeForce RTX 5080 run a 30B model?
Yes. For example a GeForce RTX 5080 runs ERNIE-4.5-VL-28B-A3B at Q3_K_M, using about 12.9 GB of memory and generating around 218 tokens per second.
How much memory does a GeForce RTX 5080 have?
A GeForce RTX 5080 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 5080?
The GeForce RTX 5080 has 960 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 5080 use?
It uses GDDR7 clocked at 1.88 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 5080?
The GeForce RTX 5080 is a NVIDIA product, with the chip manufactured by TSMC, on a 5 nm process.
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.