Calculate the TPS of the Quadro P2000 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
DeciLM 6B
5.7B · Q3_K_M · 16.4 tok/s
Fastest model
Gemma 3 QAT 1B
34.6 tok/s · 1B
Which AI models can run on a Quadro P2000 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.
97 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
34.6
tok/s
12–69 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
34.6
tok/s
12–69 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
34.6
tok/s
12–69 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
34.6
tok/s
12–69 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
34.6
tok/s
12–69 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
34.6
tok/s
12–69 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
32.0
tok/s
11–64 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
31.5
tok/s
11–63 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
31.5
tok/s
11–63 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
31.5
tok/s
11–63 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
31.5
tok/s
11–63 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
28.8
tok/s
10–58 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
28.8
tok/s
10–58 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
28.8
tok/s
10–58 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
28.8
tok/s
10–58 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
28.1
tok/s
10–56 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 54k tokens | Q8_0 | Comfortable |
|
27.7
tok/s
10–55 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
26.6
tok/s
9–53 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
26.6
tok/s
9–53 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
26.6
tok/s
9–53 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
26.6
tok/s
9–53 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
26.6
tok/s
9–53 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
26.6
tok/s
9–53 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
26.6
tok/s
9–53 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
26.6
tok/s
9–53 · 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 P2000 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
- 4 GB
- Memory bandwidth
- 96 GB/s
- Memory type
- GDDR5
- Memory bus width
- 128 bit
- Memory clock
- 1.5 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
- GP107
- Architecture
- Pascal
- Generation
- Quadro Pascal-M(Px000)
- Foundry
- Samsung
- Process size
- 14 nm
- Transistors
- 3.3 billion
- Transistor density
- 25,000 K/mm²
- Die size
- 132 mm²
- Package
- FCBGA-908
- Released
- 6 February 2017
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
- 1.56 GHz
- Boost clock
- 1.61 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
- 768
- Texture mapping units
- 48
- Render output units
- 32
- Streaming multiprocessors
- 6
- L1 cache
- 48 KB
- L2 cache
- 1 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)
- 38.6 GFLOPS
- Single precision (FP32)
- 2.5 TFLOPS
- Double precision (FP64)
- 77.1 GFLOPS
- Pixel rate
- 51 GPixel/s
- Texture rate
- 77 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)
- 50 W
- Power connectors
- None
- Bus interface
- PCIe 3.0 x16
- 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 P2000 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
4 GB
Bandwidth
96 GB/s
Largest model
DeciLM 6B
Quadro P2000 Mobile carries only 4 GB of GDDR5. That limits it to the smaller end of the catalogue, and a model has to fit entirely inside before it generates anything at all. A runtime actually gets about 3.6 GB.
Memory bandwidth reaches 96 GB/s across a bus of 128 bits. 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.
Bandwidth is clock times bus width, and this card clocks its memory at 1.5 GHz. Both halves matter, and neither is visible in a gaming benchmark.
The practical ceiling is DeciLM 6B, 5.7B, compressed to Q3_K_M and generating around 16.4 tokens per second.
The chip and how it was built
Quadro P2000 Mobile is built on the graphics processor GP107, using the architecture Pascal from NVIDIA, as part of the generation Quadro Pascal-M(Px000).
The chip is manufactured by Samsung, on a process of 14 nm, with a die measuring 132 mm², holding 3.3 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 2017, roughly 9.4817766364006 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
38.6 GFLOPS
FP64
77.1 GFLOPS
On paper Quadro P2000 Mobile reaches 38.6 GFLOPS at half precision, and 2.5 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 reaches 77.1 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 a base of 1.56 GHz to a boost of 1.61 GHz. 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
Quadro P2000 Mobile has an L1 cache of 48 KB, backed by an L2 cache of 1 MB. 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 768 shading units, 48 texture mapping units, and 32 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
50 W
Quadro P2000 Mobile is rated at 50 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 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 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 Quadro P2000 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 P2000 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 P2000 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 97 models the card handles. The search box takes a name or a size such as 27b, which matches on parameter count.
-
02
Set the context length you will actually use
Longer conversations cost memory on top of the weights. Against 4 GB it is often what pushes a large model over the edge.
-
03
Pin the comparison to one quality level
By default the table picks the least-compressed copy that fits. Setting a floor removes models that only qualify through heavy compression.
-
04
Take the range as the answer
The figures are calculated, not measured. The fastest result on this card is 34.6 tok/s on Gemma 3 QAT 1B. The same card and model vary by thirty to fifty per cent between inference runtimes.
-
05
Check the memory column before committing
The fit column separates models that just fit from those with room to spare — worth checking before settling on one, against an available 4 GB.
-
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, alongside Quadro P2000 Mobile.
Answers
Quadro P2000 Mobile — common questions
Quadro P2000 Mobile— what is the largest AI model it can run?
The largest model in our catalogue that fits is DeciLM 6B at 5.7B parameters, compressed to Q3_K_M. It generates roughly 16.4 tokens per second and needs about 3.5 GB of the card's memory.
Quadro P2000 Mobile— how many tokens per second does it produce?
It depends on the model. The fastest model we track here is Gemma 3 QAT 1B at about 34.6 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.
Quadro P2000 Mobile— how much memory does it have?
This card has 4 GB of GDDR5. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 3.6 GB available for a model and its conversation.
Quadro P2000 Mobile— what is its memory bandwidth?
Memory bandwidth reaches 96 GB/s across a bus of 128 bits. 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.
Quadro P2000 Mobile— what type of memory does it use?
It uses GDDR5 clocked at 1.5 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.
Quadro P2000 Mobile— who makes it?
This is a product of NVIDIA, with the chip manufactured by Samsung, on a process of 14 nm.
Quadro P2000 Mobile— when was it released?
It was released in February 2017.
Quadro P2000 Mobile— how much power does it use?
Rated board power is 50 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.
Quadro P2000 Mobile— how much cache does it have?
The L1 cache is 48 KB, and the L2 cache is 1 MB. 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.
Quadro P2000 Mobile— what are its TFLOPS?
It is rated at 38.6 GFLOPS at half precision and 2.5 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.
Quadro P2000 Mobile— does it support CUDA?
Yes. It 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.
Quadro P2000 Mobile— what bus interface does it 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.
Quadro P2000 Mobile— is it 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 97 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Quadro P2000 Mobile— can it run a model that does not fit in its memory?
Offloading past the card's 4 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.
Would two Quadro P2000 Mobile cards be twice as fast?
Pairing them buys headroom rather than pace: 8 GB to work with rather than twice the tokens per second — every figure here is for a single card.
Quadro P2000 Mobile— which AI models can it run?
97 of the 679 open-weight language models we track fit on this card and can be run locally. The table on this page lists every one, with the memory it needs, the quantisation it runs at and an estimated generation speed.
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.