Calculate the TPS of the RTX A4500 Max-Q on local AI models

NVIDIA 16 GB GDDR6 448 GB/s March 2022

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

432 models it can run

679 models in our catalogue altogether

Largest model it holds

Nemotron 3-Nano-30B-A3B

31.6B · Q3_K_M · 90.0 tok/s

Fastest model

Gemma 3 QAT 1B

190 tok/s · 1B

Which AI models can run on a RTX A4500 Max-Q?

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
190 tok/s

161–228

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

161–228

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

114–304 · low confidence

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

114–304 · low confidence

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

114–304 · low confidence

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

114–304 · low confidence

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

105–281 · low confidence

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

104–276 · low confidence

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

104–276 · low confidence

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

104–276 · low confidence

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

104–276 · low confidence

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

95–253 · low confidence

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

95–253 · low confidence

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

95–253 · low confidence

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

95–253 · low confidence

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

131–185

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

91–243 · low confidence

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

88–234 · low confidence

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

88–234 · low confidence

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

88–234 · low confidence

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

88–234 · low confidence

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

88–234 · low confidence

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

88–234 · low confidence

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

88–234 · low confidence

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

88–234 · 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

RTX A4500 Max-Q 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
448 GB/s
Memory type
GDDR6
Memory bus width
256 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
GA104
Architecture
Ampere
Generation
Ampere-MW(Ax000)
Foundry
Samsung
Process size
8 nm
Transistors
17.4 billion
Transistor density
44,400 K/mm²
Die size
392 mm²
Package
BGA-2713
Released
22 March 2022

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
510 MHz
Boost clock
1.22 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
5,888
Texture mapping units
184
Render output units
96
Streaming multiprocessors
46
Tensor cores
184
Ray tracing cores
46
L1 cache
128 KB
L2 cache
4 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)
14.3 TFLOPS
Single precision (FP32)
14.3 TFLOPS
Double precision (FP64)
223.6 GFLOPS
Pixel rate
117 GPixel/s
Texture rate
224 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)
80 W
Power connectors
None
Bus interface
PCIe 4.0 x16

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
8.6
DirectX
12.2
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
Shader model
6.8

Listings

Where to buy a RTX A4500 Max-Q

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

16 GB

Bandwidth

448 GB/s

Largest model

Nemotron 3-Nano-30B-A3B

16 GB of GDDR6 puts the RTX A4500 Max-Q 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.

The memory bus moves 448 GB/s across a 256-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.

That comes from a 1.75 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.

Put together, the largest model that fits is Nemotron 3-Nano-30B-A3B at 31.6B, running Q3_K_M and producing around 90.0 tokens per second.

The chip and how it was built

The RTX A4500 Max-Q is built on the GA104 graphics processor, using NVIDIA's Ampere architecture, as part of the Ampere-MW(Ax000) generation.

The chip is manufactured by Samsung, on a 8 nm process, with a die measuring 392 mm², holding 17.4 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 2022, roughly 4 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

14.3 TFLOPS

FP64

223.6 GFLOPS

Tensor cores

184

On paper the RTX A4500 Max-Q reaches 14.3 TFLOPS at half precision and 14.3 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 223.6 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 184 tensor cores across 46 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 510 MHz at base to 1.22 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 RTX A4500 Max-Q has 128 KB of L1 cache, backed by 4 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 5,888 shading units, 184 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

80 W

The RTX A4500 Max-Q is rated at 80 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.

It connects over PCIe 4.0 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 RTX A4500 Max-Q

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 North Mini Code 30B · Q3_K_M · Jun 2026 94.8 tok/s
  2. 02 Qwen 3.6-27B 27B · Q3_K_M · Apr 2026 19.0 tok/s
  3. 03 Qwen3.5-27B 27B · Q3_K_M · Feb 2026 19.0 tok/s
  4. 04 Nemotron 3-Nano-30B-A3B 31.6B · Q3_K_M · Dec 2025 90.0 tok/s
  5. 05 Nomos 1 30B · Q3_K_M · Dec 2025 94.8 tok/s
  6. 06 C2S-Scale 27B · Q3_K_M · Oct 2025 19.0 tok/s
  7. 07 Gemma-SEA-LION-v4-27B-IT 27B · Q3_K_M · Aug 2025 19.0 tok/s
  8. 08 ERNIE-4.5-VL-28B-A3B 28B · Q3_K_M · Jun 2025 102 tok/s
  9. 09 Qwen3-30B-A3B 30B · Q3_K_M · Apr 2025 94.8 tok/s
  10. 10 Gemma 3 QAT 27B 27B · Q3_K_M · Apr 2025 19.0 tok/s

The fastest AI models on a RTX A4500 Max-Q

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 190 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 190 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 190 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 190 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 190 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 190 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 176 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 172 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 172 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 172 tok/s

Step by step

How to work out the tokens per second of a RTX A4500 Max-Q

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

    Find the model in the table

    The table lists 432 models this RTX A4500 Max-Q can run. Search by name, or by size — typing 27b matches on the parameter count even when the name never states it.

  2. 02

    Set the context length you will actually use

    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.

  3. 03

    Set a minimum quality if you need one

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

  4. 04

    Take the range as the answer

    The figures are calculated, not measured. 190 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

    Read the fit verdict last

    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 16 GB available.

  6. 06

    Cross-check against other hardware

    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 RTX A4500 Max-Q compares.

Answers

RTX A4500 Max-Q — common questions

01

Would two RTX A4500 Max-Q cards be twice as fast?

No. A second RTX A4500 Max-Q doubles the memory to 32 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.

02

What AI models can a RTX A4500 Max-Q run?

432 of the 679 open-weight language models we track fit on a RTX A4500 Max-Q 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.

03

What is the largest AI model a RTX A4500 Max-Q can run?

The largest model in our catalogue that fits on a RTX A4500 Max-Q is Nemotron 3-Nano-30B-A3B at 31.6B parameters, compressed to Q3_K_M. It generates roughly 90.0 tokens per second and needs about 14.4 GB of the card's memory.

04

How many tokens per second does a RTX A4500 Max-Q produce?

It depends on the model. On a RTX A4500 Max-Q the fastest model we track is Gemma 3 QAT 1B at about 190 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.

05

Can a RTX A4500 Max-Q run a 7B model?

Yes. For example a RTX A4500 Max-Q runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 28.3 tokens per second.

06

Can a RTX A4500 Max-Q run a 13B model?

Yes. For example a RTX A4500 Max-Q runs DeepSeekMoE-16B at Q6_K, using about 13.7 GB of memory and generating around 95.7 tokens per second.

07

Can a RTX A4500 Max-Q run a 30B model?

Yes. For example a RTX A4500 Max-Q runs ERNIE-4.5-VL-28B-A3B at Q3_K_M, using about 12.9 GB of memory and generating around 102 tokens per second.

08

How much memory does a RTX A4500 Max-Q have?

A RTX A4500 Max-Q has 16 GB of GDDR6 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.

09

What is the memory bandwidth of a RTX A4500 Max-Q?

The RTX A4500 Max-Q has 448 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.

10

What type of memory does a RTX A4500 Max-Q 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.

11

Who makes the RTX A4500 Max-Q?

The RTX A4500 Max-Q is a NVIDIA product, with the chip manufactured by Samsung, on a 8 nm process.

12

When was the RTX A4500 Max-Q released?

The RTX A4500 Max-Q was released in March 2022.

13

How much power does a RTX A4500 Max-Q use?

The RTX A4500 Max-Q has a rated board power of 80 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.

14

How much cache does a RTX A4500 Max-Q have?

The RTX A4500 Max-Q has 128 KB of L1 cache, and 4 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.

15

What are the TFLOPS of a RTX A4500 Max-Q?

The RTX A4500 Max-Q is rated at 14.3 TFLOPS at half precision and 14.3 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.

16

How many tensor cores does a RTX A4500 Max-Q have?

The RTX A4500 Max-Q has 184 tensor cores across 46 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.

17

Does the RTX A4500 Max-Q support CUDA?

Yes. The RTX A4500 Max-Q reports CUDA compute capability 8.6. 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.

18

What bus interface does the RTX A4500 Max-Q use?

It uses PCIe 4.0 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.

19

Is the RTX A4500 Max-Q good for running local AI models?

Its memory covers small and mid-sized models, though the largest are out of reach and its bandwidth gives usable, if unspectacular, generation speeds. 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.

20

Can a RTX A4500 Max-Q run a model that does not fit in its memory?

It can be split, with the overflow held in system memory — but that part drags the whole thing down, and none of the 16 GB figures on this page assume it.

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