Calculate the TPS of the Steam Deck OLED 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 · 27.6 tok/s
Fastest model
Gemma 3 QAT 1B
58.1 tok/s · 1B
Which AI models can run on a Steam Deck OLED 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 | ||||||
|---|---|---|---|---|---|---|---|
|
58.1
tok/s
35–93 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
58.1
tok/s
35–93 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
58.1
tok/s
35–93 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
58.1
tok/s
35–93 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
58.1
tok/s
35–93 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
58.1
tok/s
35–93 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
53.8
tok/s
32–86 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.9
tok/s
32–85 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.9
tok/s
32–85 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.9
tok/s
32–85 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.9
tok/s
32–85 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.5
tok/s
29–78 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.5
tok/s
29–78 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.5
tok/s
29–78 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.5
tok/s
29–78 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
47.3
tok/s
28–76 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
46.6
tok/s
28–75 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.7
tok/s
27–72 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.7
tok/s
27–72 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.7
tok/s
27–72 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.7
tok/s
27–72 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.7
tok/s
27–72 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.7
tok/s
27–72 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.7
tok/s
27–72 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.7
tok/s
27–72 · 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
Steam Deck OLED 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
- 176 GB/s
- Memory type
- LPDDR5
- Memory bus width
- 128 bit
- Memory clock
- 1.38 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
- Sephiroth
- Architecture
- RDNA 2.0
- Generation
- Console GPU(Valve)
- Foundry
- TSMC
- Process size
- 6 nm
- Transistors
- 2.4 billion
- Transistor density
- 18,300 K/mm²
- Die size
- 131 mm²
- Released
- 9 November 2023
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 GHz
- Boost clock
- 1.6 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
- 512
- Texture mapping units
- 32
- Render output units
- 16
- Ray tracing cores
- 8
- L1 cache
- 128 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)
- 3.3 TFLOPS
- Single precision (FP32)
- 1.6 TFLOPS
- Double precision (FP64)
- 102.4 GFLOPS
- Pixel rate
- 26 GPixel/s
- Texture rate
- 51 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)
- 15 W
- Dimensions
- 298 mm × 49 mm
- Display outputs
- 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.
- DirectX
- 12.2
- OpenGL
- 4.6
- Vulkan
- 1.3
- OpenCL
- 2.0
- Shader model
- 6.8
Listings
Where to buy a Steam Deck OLED 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
176 GB/s
Largest model
Nemotron 3-Nano-30B-A3B
16 GB of LPDDR5 puts the Steam Deck OLED 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.
At 176 GB/s across a 128-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.
Bandwidth is clock times bus width, and this card clocks its memory at 1.38 GHz. Both halves matter, and neither is visible in a gaming benchmark.
The practical ceiling is Nemotron 3-Nano-30B-A3B at 31.6B, held at Q3_K_M and running at roughly 27.6 tokens per second.
The chip and how it was built
The Steam Deck OLED GPU is built on the Sephiroth graphics processor, using AMD's RDNA 2.0 architecture, as part of the Console GPU(Valve) generation.
The chip is manufactured by TSMC, on a 6 nm process, with a die measuring 131 mm², holding 2.4 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 November 2023, roughly 2 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
3.3 TFLOPS
FP64
102.4 GFLOPS
On paper the Steam Deck OLED GPU reaches 3.3 TFLOPS at half precision and 1.6 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 102.4 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 GHz at base to 1.6 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 Steam Deck OLED GPU has 128 KB of L1 cache, backed by 1 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 512 shading units, 32 texture mapping units, and 16 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
15 W
The Steam Deck OLED GPU is rated at 15 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 298 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 Steam Deck OLED 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 Steam Deck OLED 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 Steam Deck OLED 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
Find the model in the table
Every one of the 432 models this Steam Deck OLED GPU runs is in the table above. Search narrows it by name or by size.
-
02
Decide how long your conversations run
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
Pin the comparison to one quality level
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 58.1 tok/s on Gemma 3 QAT 1B, and which inference software you use moves that by thirty to fifty per cent.
-
05
Check the memory column before committing
Compare what each model needs with the 16 GB this card provides. Tight means it works today; comfortable means it still works when the conversation grows.
-
06
Cross-check against other hardware
Every model name in the table links to its own page, which runs the same calculation across every card we hold. That is where you see whether the Steam Deck OLED GPU is the right buy for it or merely a card that fits.
Answers
Steam Deck OLED GPU — common questions
What is the largest AI model a Steam Deck OLED GPU can run?
The largest model in our catalogue that fits on a Steam Deck OLED GPU is Nemotron 3-Nano-30B-A3B at 31.6B parameters, compressed to Q3_K_M. It generates roughly 27.6 tokens per second and needs about 14.4 GB of the card's memory.
How many tokens per second does a Steam Deck OLED GPU produce?
It depends on the model. On a Steam Deck OLED GPU the fastest model we track is Gemma 3 QAT 1B at about 58.1 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 Steam Deck OLED GPU run a 7B model?
Yes. For example a Steam Deck OLED GPU runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 8.7 tokens per second.
Can a Steam Deck OLED GPU run a 13B model?
Yes. For example a Steam Deck OLED GPU runs DeepSeekMoE-16B at Q6_K, using about 13.7 GB of memory and generating around 29.3 tokens per second.
Can a Steam Deck OLED GPU run a 30B model?
Yes. For example a Steam Deck OLED GPU runs ERNIE-4.5-VL-28B-A3B at Q3_K_M, using about 12.9 GB of memory and generating around 31.1 tokens per second.
How much memory does a Steam Deck OLED GPU have?
A Steam Deck OLED GPU has 16 GB of LPDDR5 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 Steam Deck OLED GPU?
The Steam Deck OLED GPU has 176 GB/s of memory bandwidth, across a 128-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 Steam Deck OLED GPU use?
It uses LPDDR5 clocked at 1.38 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 Steam Deck OLED GPU?
The Steam Deck OLED GPU is a AMD product, with the chip manufactured by TSMC, on a 6 nm process.
When was the Steam Deck OLED GPU released?
The Steam Deck OLED GPU was released in November 2023.
How much power does a Steam Deck OLED GPU use?
The Steam Deck OLED GPU has a rated board power of 15 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 Steam Deck OLED GPU have?
The Steam Deck OLED GPU has 128 KB of L1 cache, and 1 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 Steam Deck OLED GPU?
The Steam Deck OLED GPU is rated at 3.3 TFLOPS at half precision and 1.6 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 Steam Deck OLED GPU support CUDA?
No. CUDA is NVIDIA-only, and the Steam Deck OLED 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 Steam Deck OLED GPU 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 Steam Deck OLED 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 Steam Deck OLED GPU cards be twice as fast?
Capacity adds, throughput does not. Two of them give you 32 GB to work with rather than twice the tokens per second — every figure here is for a single Steam Deck OLED GPU.
What AI models can a Steam Deck OLED GPU run?
432 of the 679 open-weight language models we track fit on a Steam Deck OLED 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.
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.