Calculate the TPS of the Quadro P3200 Mobile on local AI models

NVIDIA 6 GB GDDR5 168 GB/s February 2018

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 · 17.0 tok/s

Fastest model

Gemma 3 QAT 1B

60.6 tok/s · 1B

Which AI models can run on a Quadro P3200 Mobile?

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
60.6 tok/s

21–121 · low confidence

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

21–121 · low confidence

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

21–121 · low confidence

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

21–121 · low confidence

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

21–121 · low confidence

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

21–121 · low confidence

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

20–112 · low confidence

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

19–110 · low confidence

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

19–110 · low confidence

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

19–110 · low confidence

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

19–110 · low confidence

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

18–101 · low confidence

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

18–101 · low confidence

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

18–101 · low confidence

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

18–101 · low confidence

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

17–98 · low confidence

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

17–97 · low confidence

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

16–93 · low confidence

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

16–93 · low confidence

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

16–93 · low confidence

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

16–93 · low confidence

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

16–93 · low confidence

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

16–93 · low confidence

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

16–93 · low confidence

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

16–93 · 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

Quadro P3200 Mobile 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
168 GB/s
Memory type
GDDR5
Memory bus width
192 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
GP104
Architecture
Pascal
Generation
Quadro Pascal-M(Px200)
Foundry
TSMC
Process size
16 nm
Transistors
7.2 billion
Transistor density
22,900 K/mm²
Die size
314 mm²
Package
BGA-2150
Released
21 February 2018

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
1.33 GHz
Boost clock
1.54 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
1,792
Texture mapping units
112
Render output units
64
Streaming multiprocessors
14
L1 cache
48 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.

Half precision (FP16)
86.4 GFLOPS
Single precision (FP32)
5.5 TFLOPS
Double precision (FP64)
172.8 GFLOPS
Pixel rate
99 GPixel/s
Texture rate
173 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)
75 W
Power connectors
None
Bus interface
MXM-B (3.0)
Slot width
MXM Module

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 Quadro P3200 Mobile

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

168 GB/s

Largest model

Qwen-VL

At 6 GB of GDDR5 the Quadro P3200 Mobile 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.

At 168 GB/s across a 192-bit bus, bandwidth is this card's real constraint. Every token requires reading the entire model out of memory, so a large model will feel slow here even when it fits.

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.

The biggest thing it holds is Qwen-VL (9.6B) at Q3_K_M compression, for about 17.0 tokens per second.

The chip and how it was built

The Quadro P3200 Mobile is built on the GP104 graphics processor, using NVIDIA's Pascal architecture, as part of the Quadro Pascal-M(Px200) generation.

The chip is manufactured by TSMC, on a 16 nm process, with a die measuring 314 mm², holding 7.2 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 February 2018, roughly 8 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

86.4 GFLOPS

FP64

172.8 GFLOPS

On paper the Quadro P3200 Mobile reaches 86.4 GFLOPS at half precision and 5.5 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 172.8 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 1.33 GHz at base to 1.54 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 Quadro P3200 Mobile has 48 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 1,792 shading units, 112 texture mapping units, and 64 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

75 W

The Quadro P3200 Mobile is rated at 75 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.

The board occupies a mxm module. 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 MXM-B (3.0). 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 Quadro P3200 Mobile

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 18.2 tok/s
  2. 02 NVIDIA-Nemotron-Nano-9B-v2 9B · Q3_K_M · Aug 2025 18.2 tok/s
  3. 03 Ovis2.5 9B 9B · Q3_K_M · Aug 2025 18.2 tok/s
  4. 04 GLM-4.1V-Thinking 9B · Q3_K_M · Aug 2025 18.2 tok/s
  5. 05 MamayLM 9B · Q3_K_M · Apr 2025 18.2 tok/s
  6. 06 GLM-4-9B-0414 9B · Q3_K_M · Apr 2025 18.2 tok/s
  7. 07 SimPO 9B · Q3_K_M · Nov 2024 18.2 tok/s
  8. 08 GLM-4V-9B 9B · Q3_K_M · Jun 2024 18.2 tok/s
  9. 09 Persimmon-8B 9.3B · Q3_K_M · Sep 2023 17.6 tok/s
  10. 10 Qwen-VL 9.6B · Q3_K_M · Aug 2023 17.0 tok/s

The fastest AI models on a Quadro P3200 Mobile

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 60.6 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 60.6 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 60.6 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 60.6 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 60.6 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 60.6 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 56.1 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 55.1 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 55.1 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 55.1 tok/s

Step by step

How to work out the tokens per second of a Quadro P3200 Mobile

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 266 models this Quadro P3200 Mobile 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

    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.

  3. 03

    Set a minimum quality if you need one

    Compression is what lets bigger models fit. The quality control drops any model that needs more of it than you are willing to give.

  4. 04

    Take the range as the answer

    The figures are calculated, not measured. 60.6 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

    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 6 GB available.

  6. 06

    Cross-check against other hardware

    Following a model through to its own page lists all the hardware that can run it, so you can see where the Quadro P3200 Mobile sits against the alternatives.

Answers

Quadro P3200 Mobile — common questions

01

What type of memory does a Quadro P3200 Mobile 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.

02

Who makes the Quadro P3200 Mobile?

The Quadro P3200 Mobile is a NVIDIA product, with the chip manufactured by TSMC, on a 16 nm process.

03

When was the Quadro P3200 Mobile released?

The Quadro P3200 Mobile was released in February 2018.

04

How much power does a Quadro P3200 Mobile use?

The Quadro P3200 Mobile has a rated board power of 75 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.

05

How much cache does a Quadro P3200 Mobile have?

The Quadro P3200 Mobile has 48 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.

06

What are the TFLOPS of a Quadro P3200 Mobile?

The Quadro P3200 Mobile is rated at 86.4 GFLOPS at half precision and 5.5 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.

07

Does the Quadro P3200 Mobile support CUDA?

Yes. The Quadro P3200 Mobile 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.

08

What bus interface does the Quadro P3200 Mobile use?

It uses MXM-B (3.0). 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.

09

Is the Quadro P3200 Mobile 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.

10

Can a Quadro P3200 Mobile 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.

11

Would two Quadro P3200 Mobile cards be twice as fast?

Pairing Quadro P3200 Mobile cards buys headroom rather than pace: 12 GB of combined memory, at roughly the same generation speed as one.

12

What AI models can a Quadro P3200 Mobile run?

266 of the 679 open-weight language models we track fit on a Quadro P3200 Mobile 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.

13

What is the largest AI model a Quadro P3200 Mobile can run?

The largest model in our catalogue that fits on a Quadro P3200 Mobile is Qwen-VL at 9.6B parameters, compressed to Q3_K_M. It generates roughly 17.0 tokens per second and needs about 5.4 GB of the card's memory.

14

How many tokens per second does a Quadro P3200 Mobile produce?

It depends on the model. On a Quadro P3200 Mobile the fastest model we track is Gemma 3 QAT 1B at about 60.6 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.

15

Can a Quadro P3200 Mobile run a 7B model?

Yes. For example a Quadro P3200 Mobile runs MetaMath 7B (Mistral finetune) at IQ4_XS, using about 5.1 GB of memory and generating around 21.2 tokens per second.

16

How much memory does a Quadro P3200 Mobile have?

A Quadro P3200 Mobile 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.

17

What is the memory bandwidth of a Quadro P3200 Mobile?

The Quadro P3200 Mobile has 168 GB/s of memory bandwidth, across a 192-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.

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