Calculate the TPS of the Xbox Series S GPU on local AI models

AMD 8 GB GDDR6 224 GB/s November 2020

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

337 models it can run

679 models in our catalogue altogether

Largest model it holds

Baichuan 1-13B

13.3B · Q3_K_M · 15.1 tok/s

Fastest model

Gemma 3 QAT 1B

74.0 tok/s · 1B

Which AI models can run on a Xbox Series S 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.

337 models match

Calculating
Quantisation Fit
74.0 tok/s

44–118 · low confidence

Gemma 3 1B 1B Mar 2025 1.8 GB 33k tokens Q8_0 Comfortable
74.0 tok/s

44–118 · low confidence

Gemma 3 QAT 1B 1B Apr 2025 1.8 GB 33k tokens Q8_0 Comfortable
74.0 tok/s

44–118 · low confidence

HGRN 1B (WT 103) 1B Nov 2023 1.8 GB 131k tokens ? Q8_0 Comfortable
74.0 tok/s

44–118 · low confidence

LLama 3..2 Typhoon 2 1B 1B Dec 2024 1.8 GB 131k tokens ? Q8_0 Comfortable
74.0 tok/s

44–118 · low confidence

OLMo-1B 1B Feb 2024 1.8 GB 131k tokens ? Q8_0 Comfortable
74.0 tok/s

44–118 · low confidence

Pythia-1b 1B Apr 2023 1.8 GB 131k tokens ? Q8_0 Comfortable
68.5 tok/s

41–110 · low confidence

OpenELM-1.1B 1.1B May 2024 1.9 GB 131k tokens ? Q8_0 Comfortable
67.3 tok/s

40–108 · low confidence

DeciCoder-1B 1.1B Aug 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
67.3 tok/s

40–108 · low confidence

SantaCoder 1.1B Jan 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
67.3 tok/s

40–108 · low confidence

TinyLlama-1.1B (1T token checkpoint) 1.1B Oct 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
67.3 tok/s

40–108 · low confidence

TinyLlama-1.1B (3T token checkpoint) 1.1B Oct 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
61.7 tok/s

37–99 · low confidence

EXAONE 4.0 (1.2B) 1.2B Jul 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
61.7 tok/s

37–99 · low confidence

MinerU2.5 1.2B Sep 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
61.7 tok/s

37–99 · low confidence

Pleias 1.0 1.2B 1.2B Dec 2024 2.0 GB 131k tokens ? Q8_0 Comfortable
61.7 tok/s

37–99 · low confidence

Pleias-RAG-1B 1.2B Apr 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
60.2 tok/s

36–96 · low confidence

Llama 3.2 1B 1.2B Sep 2024 2.2 GB 131k tokens Q8_0 Comfortable
59.3 tok/s

36–95 · low confidence

MiniCPM-1.2B 1.2B Jun 2024 2.0 GB 131k tokens ? Q8_0 Comfortable
56.9 tok/s

34–91 · low confidence

DeepSeek Coder 1.3B 1.3B Jan 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
56.9 tok/s

34–91 · low confidence

DeepSeek-VL-1.3B 1.3B Mar 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
56.9 tok/s

34–91 · low confidence

DigiRL 1.3B Jun 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
56.9 tok/s

34–91 · low confidence

GLA Transformer 1.3B 1.3B Aug 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
56.9 tok/s

34–91 · low confidence

Janus 1.3B 1.3B Oct 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
56.9 tok/s

34–91 · low confidence

Kosmos-2.5 1.3B Aug 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
56.9 tok/s

34–91 · low confidence

Otter 1.3B May 2023 2.1 GB 131k tokens ? Q8_0 Comfortable
56.9 tok/s

34–91 · 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

Xbox Series S 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
8 GB
Memory bandwidth
224 GB/s
Memory type
GDDR6
Memory bus width
128 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
Lockhart
Architecture
RDNA 2.0
Generation
Console GPU(Microsoft)
Foundry
TSMC
Process size
7 nm
Transistors
8 billion
Transistor density
40,600 K/mm²
Die size
197 mm²
Package
BGA-1303
Released
10 November 2020

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
1.57 GHz
Boost clock
1.57 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
1,280
Texture mapping units
80
Render output units
32
L2 cache
2 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)
8 TFLOPS
Single precision (FP32)
4 TFLOPS
Double precision (FP64)
250.4 GFLOPS
Pixel rate
50 GPixel/s
Texture rate
125 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)
100 W
Dimensions
274 mm × 64 mm
Display outputs
1x HDMI 2.1

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
1.2
OpenCL
1.2
Shader model
6.8

Listings

Where to buy a Xbox Series S 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

Capacity and bandwidth

Memory

8 GB

Bandwidth

224 GB/s

Largest model

Baichuan 1-13B

At 8 GB of GDDR6 the Xbox Series S GPU is limited to the smaller end of the catalogue. About 7.2 GB is actually available to a runtime, and a model has to fit entirely inside it before generating anything at all.

At 224 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 1.75 GHz. Both halves matter, and neither is visible in a gaming benchmark.

The practical ceiling is Baichuan 1-13B at 13.3B, held at Q3_K_M and running at roughly 15.1 tokens per second.

The chip and how it was built

The Xbox Series S GPU is built on the Lockhart graphics processor, using AMD's RDNA 2.0 architecture, as part of the Console GPU(Microsoft) generation.

The chip is manufactured by TSMC, on a 7 nm process, with a die measuring 197 mm², holding 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 November 2020, roughly 5 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

8 TFLOPS

FP64

250.4 GFLOPS

On paper the Xbox Series S GPU reaches 8 TFLOPS at half precision and 4 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 250.4 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 1.57 GHz at base to 1.57 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 2 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 1,280 shading units, 80 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

100 W

The Xbox Series S GPU is rated at 100 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 274 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 Xbox Series S GPU

The biggest open-weight models that fit on this card, newest first. Each is shown at the best compression the card can hold.

  1. 01 OLMo 2 Furious 13B 13B · Q3_K_M · Dec 2024 15.4 tok/s
  2. 02 Cambrian-1-13B 13B · Q3_K_M · Jun 2024 15.4 tok/s
  3. 03 Fugaku-LLM 13B · Q3_K_M · May 2024 15.4 tok/s
  4. 04 OpenThaiGPT v1.0.0 (13B) 13.1B · Q3_K_M · Apr 2024 15.2 tok/s
  5. 05 Aya 13B · Q3_K_M · Feb 2024 15.4 tok/s
  6. 06 Elyza 13B · Q3_K_M · Dec 2023 15.4 tok/s
  7. 07 NexusRaven-V2 13B · Q3_K_M · Dec 2023 15.4 tok/s
  8. 08 Baize-v2-13B (白泽) 13B · Q3_K_M · Dec 2023 15.4 tok/s
  9. 09 Stockmark-13B 13.2B · Q3_K_M · Oct 2023 15.1 tok/s
  10. 10 Baichuan 1-13B 13.3B · Q3_K_M · Jul 2023 15.1 tok/s

The fastest AI models on a Xbox Series S GPU

Where this card produces tokens quickest. Smaller models dominate here, because generating each token means reading the whole model out of memory once.

  1. 01 Gemma 3 QAT 1B 1B · Q8_0 · 1.8 GB 74.0 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 74.0 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 74.0 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 74.0 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 74.0 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 74.0 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 68.5 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 67.3 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 67.3 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 67.3 tok/s

Step by step

How to work out the tokens per second of a Xbox Series S 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.

  1. 01

    Search for the model you want

    Every one of the 337 models this Xbox Series S GPU runs is in the table above. Search narrows it by name or by size.

  2. 02

    Match the context to your work

    Drag the slider to the conversation length you plan to work at. The cache grows with the conversation, and on 8 GB it is often what pushes a large model over the edge.

  3. 03

    Set a minimum quality if you need one

    Compression is what lets bigger models fit. The quality control drops any model that needs more of it than you are willing to give.

  4. 04

    Take the range as the answer

    The figures are calculated, not measured. 74.0 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.

  5. 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 8 GB available.

  6. 06

    Open the model to compare cards

    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 Xbox Series S GPU is the right buy for it or merely a card that fits.

Answers

Xbox Series S GPU — common questions

01

What is the largest AI model a Xbox Series S GPU can run?

The largest model in our catalogue that fits on a Xbox Series S GPU is Baichuan 1-13B at 13.3B parameters, compressed to Q3_K_M. It generates roughly 15.1 tokens per second and needs about 7.2 GB of the card's memory.

02

How many tokens per second does a Xbox Series S GPU produce?

It depends on the model. On a Xbox Series S GPU the fastest model we track is Gemma 3 QAT 1B at about 74.0 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.

03

Can a Xbox Series S GPU run a 7B model?

Yes. For example a Xbox Series S GPU runs MetaMath 7B (LLaMa finetune) at Q4_K_M, using about 6.5 GB of memory and generating around 24.4 tokens per second.

04

Can a Xbox Series S GPU run a 13B model?

Yes. For example a Xbox Series S GPU runs Gemma 4 12B at Q3_K_M, using about 6.5 GB of memory and generating around 16.7 tokens per second.

05

How much memory does a Xbox Series S GPU have?

A Xbox Series S GPU has 8 GB of GDDR6 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 7.2 GB available for a model and its conversation.

06

What is the memory bandwidth of a Xbox Series S GPU?

The Xbox Series S GPU has 224 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.

07

What type of memory does a Xbox Series S 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.

08

Who makes the Xbox Series S GPU?

The Xbox Series S GPU is a AMD product, with the chip manufactured by TSMC, on a 7 nm process.

09

When was the Xbox Series S GPU released?

The Xbox Series S GPU was released in November 2020.

10

How much power does a Xbox Series S GPU use?

The Xbox Series S GPU has a rated board power of 100 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.

11

How much cache does a Xbox Series S GPU have?

and 2 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.

12

What are the TFLOPS of a Xbox Series S GPU?

The Xbox Series S GPU is rated at 8 TFLOPS at half precision and 4 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.

13

Does the Xbox Series S GPU support CUDA?

No. CUDA is NVIDIA-only, and the Xbox Series S 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.

14

Is the Xbox Series S GPU 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 337 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.

15

Can a Xbox Series S GPU run a model that does not fit in its memory?

Only partly. Layers beyond the 8 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.

16

Would two Xbox Series S GPU cards be twice as fast?

No. A second Xbox Series S GPU doubles the memory to 16 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.

17

What AI models can a Xbox Series S GPU run?

337 of the 679 open-weight language models we track fit on a Xbox Series S 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.

All GPUs