Calculate the TPS of the Quadro P6000 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
Mixtral 8x7B
46.7B · Q3_K_M · 32.6 tok/s
Fastest model
Gemma 3 QAT 1B
156 tok/s · 1B
Which AI models can run on a Quadro P6000?
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.
502 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
156
tok/s
55–312 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
156
tok/s
55–312 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
156
tok/s
55–312 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
156
tok/s
55–312 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
156
tok/s
55–312 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
156
tok/s
55–312 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
144
tok/s
50–289 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
50–283 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
50–283 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
50–283 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
50–283 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
130
tok/s
45–260 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
130
tok/s
45–260 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
130
tok/s
45–260 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
130
tok/s
45–260 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
127
tok/s
44–253 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
125
tok/s
44–250 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
120
tok/s
42–240 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
120
tok/s
42–240 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
120
tok/s
42–240 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
120
tok/s
42–240 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
120
tok/s
42–240 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
120
tok/s
42–240 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
120
tok/s
42–240 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
120
tok/s
42–240 · 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 P6000 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
- 24 GB
- Memory bandwidth
- 433 GB/s
- Memory type
- GDDR5X
- Memory bus width
- 384 bit
- Memory clock
- 1.13 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
- GP102
- Architecture
- Pascal
- Generation
- Quadro Pascal(Px000)
- Foundry
- TSMC
- Process size
- 16 nm
- Transistors
- 11.8 billion
- Transistor density
- 25,100 K/mm²
- Die size
- 471 mm²
- Package
- BGA-2397
- Released
- 1 October 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
- 1.51 GHz
- Boost clock
- 1.65 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
- 3,840
- Texture mapping units
- 240
- Render output units
- 96
- Streaming multiprocessors
- 30
- L1 cache
- 48 KB
- L2 cache
- 3 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)
- 197.4 GFLOPS
- Single precision (FP32)
- 12.6 TFLOPS
- Double precision (FP64)
- 394.8 GFLOPS
- Pixel rate
- 158 GPixel/s
- Texture rate
- 395 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)
- 250 W
- Suggested power supply
- 600 W
- Power connectors
- 1x 8-pin
- Bus interface
- PCIe 3.0 x16
- Slot width
- Dual-slot
- Dimensions
- 267 mm
- Display outputs
- 1x DVI, 4x DisplayPort 1.4a
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 P6000
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
24 GB
Bandwidth
433 GB/s
Largest model
Mixtral 8x7B
The Quadro P6000 carries 24 GB of GDDR5X, which covers the mid-sized models most people actually run — about 21.6 GB of it after the runtime and driver reserve their working space.
The memory bus moves 433 GB/s across a 384-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.
The figure is the memory clock — 1.13 GHz here — multiplied by the bus width. It is why core counts predict generation speed so poorly.
Put together, the largest model that fits is Mixtral 8x7B at 46.7B, running Q3_K_M and producing around 32.6 tokens per second.
The chip and how it was built
The Quadro P6000 is built on the GP102 graphics processor, using NVIDIA's Pascal architecture, as part of the Quadro Pascal(Px000) generation.
The chip is manufactured by TSMC, on a 16 nm process, with a die measuring 471 mm², holding 11.8 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 October 2016, roughly 9 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
197.4 GFLOPS
FP64
394.8 GFLOPS
On paper the Quadro P6000 reaches 197.4 GFLOPS at half precision and 12.6 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 is 394.8 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 1.51 GHz at base to 1.65 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 P6000 has 48 KB of L1 cache, backed by 3 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 3,840 shading units, 240 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
250 W
The Quadro P6000 is rated at 250 W, with a 600 W power supply suggested for the whole system. 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 dual-slot, measuring 267 mm long, and needs 1x 8-pin. 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 P6000
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 P6000
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 P6000
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
Every one of the 502 models this Quadro P6000 runs is in the table above. Search narrows it by name or by size.
-
02
Set the context length you will actually use
Set the context to your real working length. Short questions cost almost nothing; a long document can consume a large share of the card's 24 GB.
-
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
Look at the range, not just the number
The figures are calculated, not measured. 156 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.
-
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 24 GB available.
-
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 P6000 sits against the alternatives.
Answers
Quadro P6000 — common questions
Would two Quadro P6000 cards be twice as fast?
No. A second Quadro P6000 doubles the memory to 48 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.
What AI models can a Quadro P6000 run?
502 of the 679 open-weight language models we track fit on a Quadro P6000 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 P6000 can run?
The largest model in our catalogue that fits on a Quadro P6000 is Mixtral 8x7B at 46.7B parameters, compressed to Q3_K_M. It generates roughly 32.6 tokens per second and needs about 21.0 GB of the card's memory.
How many tokens per second does a Quadro P6000 produce?
It depends on the model. On a Quadro P6000 the fastest model we track is Gemma 3 QAT 1B at about 156 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 P6000 run a 7B model?
Yes. For example a Quadro P6000 runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 23.3 tokens per second.
Can a Quadro P6000 run a 13B model?
Yes. For example a Quadro P6000 runs DeepSeekMoE-16B at Q8_0, using about 17.5 GB of memory and generating around 54.1 tokens per second.
Can a Quadro P6000 run a 30B model?
Yes. For example a Quadro P6000 runs Nemotron 3-Nano-30B-A3B at Q4_K_M, using about 18.1 GB of memory and generating around 63.2 tokens per second.
How much memory does a Quadro P6000 have?
A Quadro P6000 has 24 GB of GDDR5X memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 21.6 GB available for a model and its conversation.
What is the memory bandwidth of a Quadro P6000?
The Quadro P6000 has 433 GB/s of memory bandwidth, across a 384-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 P6000 use?
It uses GDDR5X clocked at 1.13 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 P6000?
The Quadro P6000 is a NVIDIA product, with the chip manufactured by TSMC, on a 16 nm process.
When was the Quadro P6000 released?
The Quadro P6000 was released in October 2016.
How much power does a Quadro P6000 use?
The Quadro P6000 has a rated board power of 250 W, and a 600 W system power supply is suggested. 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 P6000 have?
The Quadro P6000 has 48 KB of L1 cache, and 3 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 P6000?
The Quadro P6000 is rated at 197.4 GFLOPS at half precision and 12.6 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.
Does the Quadro P6000 support CUDA?
Yes. The Quadro P6000 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.
What bus interface does the Quadro P6000 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.
Is the Quadro P6000 good for running local AI models?
Its memory comfortably covers the mid-sized models most people run locally and its bandwidth gives usable, if unspectacular, generation speeds. In total it runs 502 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 P6000 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 24 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.