Calculate the TPS of the Quadro P5200 Mobile 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
Nemotron 3-Nano-30B-A3B
31.6B · Q3_K_M · 39.4 tok/s
Fastest model
Gemma 3 QAT 1B
83.1 tok/s · 1B
Which AI models can run on a Quadro P5200 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.
432 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
83.1
tok/s
29–166 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
83.1
tok/s
29–166 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
83.1
tok/s
29–166 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
83.1
tok/s
29–166 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
83.1
tok/s
29–166 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
83.1
tok/s
29–166 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
77.0
tok/s
27–154 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
75.6
tok/s
26–151 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
75.6
tok/s
26–151 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
75.6
tok/s
26–151 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
75.6
tok/s
26–151 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
69.3
tok/s
24–139 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
69.3
tok/s
24–139 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
69.3
tok/s
24–139 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
69.3
tok/s
24–139 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
67.6
tok/s
24–135 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
66.6
tok/s
23–133 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
63.9
tok/s
22–128 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
63.9
tok/s
22–128 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
63.9
tok/s
22–128 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
63.9
tok/s
22–128 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
63.9
tok/s
22–128 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
63.9
tok/s
22–128 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
63.9
tok/s
22–128 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
63.9
tok/s
22–128 · 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 P5200 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
- 16 GB
- Memory bandwidth
- 231 GB/s
- Memory type
- GDDR5
- Memory bus width
- 256 bit
- Memory clock
- 1.8 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
- 1.58 GHz
- Boost clock
- 1.76 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
- 2,560
- Texture mapping units
- 160
- Render output units
- 64
- Streaming multiprocessors
- 20
- L1 cache
- 48 KB
- L2 cache
- 2 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)
- 140.7 GFLOPS
- Single precision (FP32)
- 9 TFLOPS
- Double precision (FP64)
- 281.4 GFLOPS
- Pixel rate
- 113 GPixel/s
- Texture rate
- 281 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)
- 100 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 P5200 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
16 GB
Bandwidth
231 GB/s
Largest model
Nemotron 3-Nano-30B-A3B
16 GB of GDDR5 puts the Quadro P5200 Mobile 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.
At 231 GB/s across a 256-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.
The figure is the memory clock — 1.8 GHz here — multiplied by the bus width. It is why core counts predict generation speed so poorly.
The biggest thing it holds is Nemotron 3-Nano-30B-A3B (31.6B) at Q3_K_M compression, for about 39.4 tokens per second.
The chip and how it was built
The Quadro P5200 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
140.7 GFLOPS
FP64
281.4 GFLOPS
On paper the Quadro P5200 Mobile reaches 140.7 GFLOPS at half precision and 9 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 281.4 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 1.58 GHz at base to 1.76 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 P5200 Mobile has 48 KB of L1 cache, backed by 2 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 2,560 shading units, 160 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
100 W
The Quadro P5200 Mobile is rated at 100 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 P5200 Mobile
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 Quadro P5200 Mobile
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 Quadro P5200 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.
-
01
Start with the model, not the specification
The table lists 432 models this Quadro P5200 Mobile can run. Search by name, or by size — typing 27b matches on the parameter count even when the name never states it.
-
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.
-
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.
-
04
Take the range as the answer
Speeds come with error bars for a reason. The best case here is 83.1 tok/s on Gemma 3 QAT 1B, and which inference software you use moves that by thirty to fifty per cent.
-
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 16 GB available.
-
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 Quadro P5200 Mobile sits against the alternatives.
Answers
Quadro P5200 Mobile — common questions
What bus interface does the Quadro P5200 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.
Is the Quadro P5200 Mobile good for running local AI models?
Its memory covers small and mid-sized models, though the largest are out of reach though its bandwidth means generation will feel slow on larger models. 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 Quadro P5200 Mobile run a model that does not fit in its memory?
Only partly. Layers beyond the 16 GB sit in system memory and run at a fraction of the speed, so a mostly-offloaded model is rarely worth using. Every figure here assumes it is fully resident on the card.
Would two Quadro P5200 Mobile cards be twice as fast?
Pairing Quadro P5200 Mobile cards buys headroom rather than pace: 32 GB of combined memory, at roughly the same generation speed as one.
What AI models can a Quadro P5200 Mobile run?
432 of the 679 open-weight language models we track fit on a Quadro P5200 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.
What is the largest AI model a Quadro P5200 Mobile can run?
The largest model in our catalogue that fits on a Quadro P5200 Mobile is Nemotron 3-Nano-30B-A3B at 31.6B parameters, compressed to Q3_K_M. It generates roughly 39.4 tokens per second and needs about 14.4 GB of the card's memory.
How many tokens per second does a Quadro P5200 Mobile produce?
It depends on the model. On a Quadro P5200 Mobile the fastest model we track is Gemma 3 QAT 1B at about 83.1 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 Quadro P5200 Mobile run a 7B model?
Yes. For example a Quadro P5200 Mobile runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 12.4 tokens per second.
Can a Quadro P5200 Mobile run a 13B model?
Yes. For example a Quadro P5200 Mobile runs DeepSeekMoE-16B at Q6_K, using about 13.7 GB of memory and generating around 41.9 tokens per second.
Can a Quadro P5200 Mobile run a 30B model?
Yes. For example a Quadro P5200 Mobile runs ERNIE-4.5-VL-28B-A3B at Q3_K_M, using about 12.9 GB of memory and generating around 44.5 tokens per second.
How much memory does a Quadro P5200 Mobile have?
A Quadro P5200 Mobile has 16 GB of GDDR5 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 Quadro P5200 Mobile?
The Quadro P5200 Mobile has 231 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 Quadro P5200 Mobile use?
It uses GDDR5 clocked at 1.8 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 Quadro P5200 Mobile?
The Quadro P5200 Mobile is a NVIDIA product, with the chip manufactured by TSMC, on a 16 nm process.
When was the Quadro P5200 Mobile released?
The Quadro P5200 Mobile was released in February 2018.
How much power does a Quadro P5200 Mobile use?
The Quadro P5200 Mobile has a rated board power of 100 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.
How much cache does a Quadro P5200 Mobile have?
The Quadro P5200 Mobile has 48 KB of L1 cache, and 2 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 Quadro P5200 Mobile?
The Quadro P5200 Mobile is rated at 140.7 GFLOPS at half precision and 9 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.
Does the Quadro P5200 Mobile support CUDA?
Yes. The Quadro P5200 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.
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.