Calculate the TPS of the Playstation 5 GPU 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 · 70.2 tok/s
Fastest model
Gemma 3 QAT 1B
148 tok/s · 1B
Which AI models can run on a Playstation 5 GPU?
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 | ||||||
|---|---|---|---|---|---|---|---|
|
148
tok/s
89–237 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
148
tok/s
89–237 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
148
tok/s
89–237 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
148
tok/s
89–237 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
148
tok/s
89–237 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
148
tok/s
89–237 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
137
tok/s
82–219 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
135
tok/s
81–215 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
135
tok/s
81–215 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
135
tok/s
81–215 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
135
tok/s
81–215 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
123
tok/s
74–197 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
123
tok/s
74–197 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
123
tok/s
74–197 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
123
tok/s
74–197 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
120
tok/s
72–193 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
119
tok/s
71–190 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
114
tok/s
68–182 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
114
tok/s
68–182 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
114
tok/s
68–182 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
114
tok/s
68–182 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
114
tok/s
68–182 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
114
tok/s
68–182 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
114
tok/s
68–182 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
114
tok/s
68–182 · 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
Playstation 5 GPU 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
- 448 GB/s
- Memory type
- GDDR6
- Memory bus width
- 256 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
- Oberon Plus
- Architecture
- RDNA 2.0
- Generation
- Console GPU(Sony)
- Foundry
- TSMC
- Process size
- 6 nm
- Transistors
- 10.6 billion
- Transistor density
- 40,800 K/mm²
- Die size
- 260 mm²
- Released
- 28 September 2022
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
- 2.23 GHz
- Boost clock
- 2.23 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
- 2,304
- Texture mapping units
- 144
- Render output units
- 64
- 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)
- 20.6 TFLOPS
- Single precision (FP32)
- 10.3 TFLOPS
- Double precision (FP64)
- 643.1 GFLOPS
- Pixel rate
- 143 GPixel/s
- Texture rate
- 322 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)
- 180 W
- Dimensions
- 390 mm × 104 mm
- Display outputs
- 1x HDMI 2.1, 1x USB Type-C
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.
- OpenGL
- 4.6
- Vulkan
- 1.2
- OpenCL
- 1.2
Listings
Where to buy a Playstation 5 GPU
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
16 GB
Bandwidth
448 GB/s
Largest model
Nemotron 3-Nano-30B-A3B
16 GB of GDDR6 puts the Playstation 5 GPU 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.
The memory bus moves 448 GB/s across a 256-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.
Bandwidth is clock times bus width, and this card clocks its memory at 1.75 GHz. Both halves matter, and neither is visible in a gaming benchmark.
The biggest thing it holds is Nemotron 3-Nano-30B-A3B (31.6B) at Q3_K_M compression, for about 70.2 tokens per second.
The chip and how it was built
The Playstation 5 GPU is built on the Oberon Plus graphics processor, using AMD's RDNA 2.0 architecture, as part of the Console GPU(Sony) generation.
The chip is manufactured by TSMC, on a 6 nm process, with a die measuring 260 mm², holding 10.6 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 September 2022, roughly 3 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
20.6 TFLOPS
FP64
643.1 GFLOPS
On paper the Playstation 5 GPU reaches 20.6 TFLOPS at half precision and 10.3 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 643.1 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 2.23 GHz at base to 2.23 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
backed by 4 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 2,304 shading units, 144 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
180 W
The Playstation 5 GPU is rated at 180 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.
measuring 390 mm long. 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.
The extremes
The largest AI models that run on a Playstation 5 GPU
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 Playstation 5 GPU
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 Playstation 5 GPU
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
All 432 models the Playstation 5 GPU handles are already listed. The search box takes a name or a size such as 27b, which matches on parameter count.
-
02
Decide how long your conversations run
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 16 GB.
-
03
Set a minimum quality if you need one
Each model is shown at the best compression this card can hold. A minimum quality hides the ones that only fit by being squeezed further than you would accept.
-
04
Look at the range, not just the number
Speeds come with error bars for a reason. The best case here is 148 tok/s on Gemma 3 QAT 1B, and which inference software you use moves that by thirty to fifty per cent.
-
05
Read the fit verdict last
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
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, and how the Playstation 5 GPU compares.
Answers
Playstation 5 GPU — common questions
Can a Playstation 5 GPU run a 7B model?
Yes. For example a Playstation 5 GPU runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 22.1 tokens per second.
Can a Playstation 5 GPU run a 13B model?
Yes. For example a Playstation 5 GPU runs DeepSeekMoE-16B at Q6_K, using about 13.7 GB of memory and generating around 74.7 tokens per second.
Can a Playstation 5 GPU run a 30B model?
Yes. For example a Playstation 5 GPU runs ERNIE-4.5-VL-28B-A3B at Q3_K_M, using about 12.9 GB of memory and generating around 79.2 tokens per second.
How much memory does a Playstation 5 GPU have?
A Playstation 5 GPU has 16 GB of GDDR6 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 Playstation 5 GPU?
The Playstation 5 GPU has 448 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 Playstation 5 GPU use?
It uses GDDR6 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.
Who makes the Playstation 5 GPU?
The Playstation 5 GPU is a AMD product, with the chip manufactured by TSMC, on a 6 nm process.
When was the Playstation 5 GPU released?
The Playstation 5 GPU was released in September 2022.
How much power does a Playstation 5 GPU use?
The Playstation 5 GPU has a rated board power of 180 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 Playstation 5 GPU have?
and 4 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 Playstation 5 GPU?
The Playstation 5 GPU is rated at 20.6 TFLOPS at half precision and 10.3 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 Playstation 5 GPU support CUDA?
No. CUDA is NVIDIA-only, and the Playstation 5 GPU is a AMD card. It runs language models through ROCm, Vulkan or Metal depending on the software, which are less mature than the CUDA path — our estimates apply a penalty for that.
Is the Playstation 5 GPU 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 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 Playstation 5 GPU 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 Playstation 5 GPU cards be twice as fast?
No. A second Playstation 5 GPU doubles the memory to 32 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 Playstation 5 GPU run?
432 of the 679 open-weight language models we track fit on a Playstation 5 GPU 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 Playstation 5 GPU can run?
The largest model in our catalogue that fits on a Playstation 5 GPU is Nemotron 3-Nano-30B-A3B at 31.6B parameters, compressed to Q3_K_M. It generates roughly 70.2 tokens per second and needs about 14.4 GB of the card's memory.
How many tokens per second does a Playstation 5 GPU produce?
It depends on the model. On a Playstation 5 GPU the fastest model we track is Gemma 3 QAT 1B at about 148 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.
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.