Calculate the TPS of the Tesla P100 SXM2 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
721 models in our catalogue altogether
Largest model it holds
Nemotron 3-Nano-30B-A3B
31.6B · Q3_K_M · 125 tok/s
Fastest model
Gemma 3 QAT 1B
264 tok/s · 1B
Which AI models can run on a Tesla P100 SXM2?
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.
455 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
264
tok/s
92–527 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
264
tok/s
92–527 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
264
tok/s
92–527 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
264
tok/s
92–527 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
264
tok/s
92–527 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
264
tok/s
92–527 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
244
tok/s
85–488 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
240
tok/s
84–479 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
240
tok/s
84–479 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
240
tok/s
84–479 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
240
tok/s
84–479 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
220
tok/s
77–439 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
220
tok/s
77–439 · low confidence |
LFM2-1.2B ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
220
tok/s
77–439 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
220
tok/s
77–439 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
220
tok/s
77–439 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
214
tok/s
75–429 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
211
tok/s
74–423 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
203
tok/s
71–406 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
203
tok/s
71–406 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
203
tok/s
71–406 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
203
tok/s
71–406 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
203
tok/s
71–406 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
203
tok/s
71–406 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
203
tok/s
71–406 · low confidence |
Otter ≈ | 1.3B | May 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
Tesla P100 SXM2 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
- 732 GB/s
- Memory type
- HBM2
- Memory bus width
- 4,096 bit
- Memory clock
- 715 MHz
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
- GP100
- Architecture
- Pascal
- Generation
- Tesla Pascal(Pxx)
- Foundry
- TSMC
- Process size
- 16 nm
- Transistors
- 15.3 billion
- Transistor density
- 25,100 K/mm²
- Die size
- 610 mm²
- Package
- BGA-2621
- Released
- 5 April 2016
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
- 1.48 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
- 3,584
- Texture mapping units
- 224
- Render output units
- 96
- Streaming multiprocessors
- 56
- L1 cache
- 24 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)
- 21.2 TFLOPS
- Single precision (FP32)
- 10.6 TFLOPS
- Double precision (FP64)
- 5.3 TFLOPS
- Pixel rate
- 142 GPixel/s
- Texture rate
- 332 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)
- 300 W
- Suggested power supply
- 700 W
- Power connectors
- None
- Bus interface
- PCIe 3.0 x16
- Slot width
- SXM 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
- 6.0
- DirectX
- 12.1
- OpenGL
- 4.6
- Vulkan
- 1.3
- OpenCL
- 3.0
- Shader model
- 6.0
Listings
Where to buy a Tesla P100 SXM2
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
732 GB/s
Largest model
Nemotron 3-Nano-30B-A3B
Tesla P100 SXM2 carries 16 GB of HBM2. That reaches comfortably into small and mid-sized models, though the largest stay out of reach without splitting them. Driver overhead leaves roughly 14.4 GB.
Memory bandwidth reaches 732 GB/s across a bus of 4,096 bits. That is the number governing generation speed — arithmetic per byte read is small enough that the bus, not the cores, is what everything waits on.
The figure is the bus width multiplied by a memory clock of 715 MHz. Both halves matter, and neither is visible in a gaming benchmark.
The biggest thing it holds is Nemotron 3-Nano-30B-A3B, 31.6B, compressed to Q3_K_M and generating around 125 tokens per second.
The chip and how it was built
Tesla P100 SXM2 is built on the graphics processor GP100, using the architecture Pascal from NVIDIA, as part of the generation Tesla Pascal(Pxx).
The chip is manufactured by TSMC, on a process of 16 nm, with a die measuring 610 mm², holding 15.3 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 April 2016, roughly 10.442988092652 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
21.2 TFLOPS
FP64
5.3 TFLOPS
On paper Tesla P100 SXM2 reaches 21.2 TFLOPS at half precision, and 10.6 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 5.3 TFLOPS. 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 1.33 GHz to a boost of 1.48 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
Tesla P100 SXM2 has an L1 cache of 24 KB, backed by an L2 cache of 4 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 3,584 shading units, 224 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
300 W
Tesla P100 SXM2 is rated at 300 W, and the suggested system power supply is 700 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 sxm 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 Tesla P100 SXM2
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 Tesla P100 SXM2
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 Tesla P100 SXM2
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 455 models this card runs. Search narrows the list by name or by size.
-
02
Decide how long your conversations run
Set the context to your real working length. Short questions cost almost nothing, but a long document can consume a large share of 16 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 264 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
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 an available 16 GB.
-
06
Check the same model from the other side
Each model page repeats this calculation for the whole catalogue. Worth a look before deciding: it shows what else runs the same model, alongside Tesla P100 SXM2.
Answers
Tesla P100 SXM2 — common questions
Tesla P100 SXM2— can it run 30B models?
Yes. For example it runs ERNIE-4.5-VL-28B-A3B at Q3_K_M, using about 12.9 GB of memory and generating around 141 tokens per second.
Tesla P100 SXM2— how much memory does it have?
This card has 16 GB of HBM2. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 14.4 GB available for a model and its conversation.
Tesla P100 SXM2— what is its memory bandwidth?
Memory bandwidth reaches 732 GB/s across a bus of 4,096 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.
Tesla P100 SXM2— what type of memory does it use?
It uses HBM2 clocked at 715 MHz. 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.
Tesla P100 SXM2— who makes it?
This is a product of NVIDIA, with the chip manufactured by TSMC, on a process of 16 nm.
Tesla P100 SXM2— when was it released?
It was released in April 2016.
Tesla P100 SXM2— how much power does it use?
Rated board power is 300 W, and the suggested system power supply is 700 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.
Tesla P100 SXM2— how much cache does it have?
The L1 cache is 24 KB, and the L2 cache is 4 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.
Tesla P100 SXM2— what are its TFLOPS?
It is rated at 21.2 TFLOPS at half precision and 10.6 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.
Tesla P100 SXM2— does it support CUDA?
Yes. It reports CUDA compute capability 6.0, 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.
Tesla P100 SXM2— 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.
Tesla P100 SXM2— is it 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 455 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Tesla P100 SXM2— can it run a model that does not fit in its memory?
Offloading past the card's 16 GB drags the whole thing down, and none of the figures on this page assume it.
Would two Tesla P100 SXM2 cards be twice as fast?
Pairing them buys headroom rather than pace: 32 GB to work with rather than twice the tokens per second — every figure here is for a single card.
Tesla P100 SXM2— which AI models can it run?
455 of the 721 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.
Tesla P100 SXM2— what is the largest AI model it can run?
The largest model in our catalogue that fits is Nemotron 3-Nano-30B-A3B at 31.6B parameters, compressed to Q3_K_M. It generates roughly 125 tokens per second and needs about 14.4 GB of the card's memory.
Tesla P100 SXM2— 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 264 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.
Tesla P100 SXM2— can it run 7B models?
Yes. For example it runs Gemma 4 E4B at Q8_0, using about 9.8 GB of memory and generating around 58.6 tokens per second.
Tesla P100 SXM2— can it run 13B models?
Yes. For example it runs DeepSeekMoE-16B at Q6_K, using about 13.7 GB of memory and generating around 133 tokens per second.
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.