Calculate the TPS of the Xbox One X GPU on local AI models

AMD 12 GB GDDR5 326 GB/s November 2017

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

411 models it can run

721 models in our catalogue altogether

Largest model it holds

ERNIE-4.5-21B-A3B

21B · Q3_K_M · 77.0 tok/s

Fastest model

Gemma 3 QAT 1B

108 tok/s · 1B

Which AI models can run on a Xbox One X 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.

411 models match

Calculating
Quantisation Fit
108 tok/s

65–173 · low confidence

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

65–173 · low confidence

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

65–173 · low confidence

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

65–173 · low confidence

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

65–173 · low confidence

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

65–173 · low confidence

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

60–160 · low confidence

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

59–157 · low confidence

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

59–157 · low confidence

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

59–157 · low confidence

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

59–157 · low confidence

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

54–144 · low confidence

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

54–144 · low confidence

LFM2-1.2B 1.2B Jul 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
89.9 tok/s

54–144 · low confidence

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

54–144 · low confidence

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

54–144 · low confidence

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

53–140 · low confidence

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

52–138 · low confidence

DeepSeekMoE-16B 16B Jan 2024 10.0 GB 4k tokens Q4_K_M Tight
86.4 tok/s

52–138 · low confidence

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

50–133 · low confidence

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

50–133 · low confidence

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

50–133 · low confidence

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

50–133 · low confidence

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

50–133 · low confidence

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

50–133 · low confidence

Kosmos-2.5 1.3B Aug 2024 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 One X 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
12 GB
Memory bandwidth
326 GB/s
Memory type
GDDR5
Memory bus width
384 bit
Memory clock
1.7 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
Scorpio
Architecture
GCN 2.0
Generation
Console GPU(Microsoft)
Foundry
TSMC
Process size
16 nm
Transistors
7 billion
Transistor density
19,500 K/mm²
Die size
359 mm²
Package
BGA-2409
Released
7 November 2017

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
1.17 GHz
Boost clock
1.17 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
2,560
Texture mapping units
160
Render output units
32

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)
6 TFLOPS
Single precision (FP32)
6 TFLOPS
Pixel rate
38 GPixel/s
Texture rate
188 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)
150 W
Dimensions
300 mm × 60 mm
Display outputs
1x HDMI 2.0b

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
12.0
Vulkan
1.1
OpenCL
1.2
Shader model
6.0

Listings

Where to buy a Xbox One X 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

Memory: the specification that decides everything

Memory

12 GB

Bandwidth

326 GB/s

Largest model

ERNIE-4.5-21B-A3B

Xbox One X GPU carries 12 GB of GDDR5. That reaches comfortably into small and mid-sized models, though the largest stay out of reach without splitting them. Driver overhead leaves roughly 10.8 GB.

Memory bandwidth reaches 326 GB/s across a bus of 384 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.

That comes from a memory clock of 1.7 GHz. Both halves matter, and neither is visible in a gaming benchmark.

The practical ceiling is ERNIE-4.5-21B-A3B, 21B, compressed to Q3_K_M and generating around 77.0 tokens per second.

The chip and how it was built

Xbox One X GPU is built on the graphics processor Scorpio, using the architecture GCN 2.0 from AMD, as part of the generation Console GPU(Microsoft).

The chip is manufactured by TSMC, on a process of 16 nm, with a die measuring 359 mm², holding 7 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 2017, roughly 8.8512044034528 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

6 TFLOPS

On paper Xbox One X GPU reaches 6 TFLOPS at half precision, and 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.

Clocks run from a base of 1.17 GHz to a boost of 1.17 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

There are 2,560 shading units, 160 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

150 W

Xbox One X GPU is rated at 150 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 300 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 One X 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 ERNIE-4.5-21B-A3B 21B · Q3_K_M · Jun 2025 77.0 tok/s
  2. 02 GigaChat Lite (GigaChat-20B-A3B) 20B · Q3_K_M · Dec 2024 80.8 tok/s
  3. 03 InternLM2.5 20B · Q3_K_M · Aug 2024 14.6 tok/s
  4. 04 Granite 20B 20B · Q3_K_M · May 2024 14.6 tok/s
  5. 05 InternLM2-20B 20B · Q3_K_M · Jan 2024 14.6 tok/s
  6. 06 CogAgent 18B · IQ4_XS · Dec 2023 14.7 tok/s
  7. 07 SPHINX (Llama 2 13B) 19.9B · Q3_K_M · Nov 2023 14.6 tok/s
  8. 08 CogVLM-17B 17B · IQ4_XS · Nov 2023 15.6 tok/s
  9. 09 Flan UL2 19.5B · Q3_K_M · Mar 2023 14.9 tok/s
  10. 10 Palmyra Large 20B 20B · Q3_K_M · Mar 2023 14.6 tok/s

The fastest AI models on a Xbox One X 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 108 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 108 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 108 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 108 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 108 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 108 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 99.8 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 98.0 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 98.0 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 98.0 tok/s

Step by step

How to work out the tokens per second of a Xbox One X 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

    Find the model in the table

    The table lists 411 models this card runs. Search narrows the list by name or by size.

  2. 02

    Match the context to your work

    Longer conversations cost memory on top of the weights. Against 12 GB so the setting is worth getting right.

  3. 03

    Choose how far you will compress

    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.

  4. 04

    Look at the range, not just the number

    The figures are calculated, not measured. The fastest result on this card is 108 tok/s on Gemma 3 QAT 1B. The same card and model vary by thirty to fifty per cent between inference runtimes.

  5. 05

    Check the headroom before you decide

    Tight means it works today; comfortable means it still works when the conversation grows. Compare what each model needs against an available 12 GB.

  6. 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 Xbox One X GPU.

Answers

Xbox One X GPU — common questions

01

Xbox One X GPU— what is its memory bandwidth?

Memory bandwidth reaches 326 GB/s across a bus of 384 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.

02

Xbox One X GPU— what type of memory does it use?

It uses GDDR5 clocked at 1.7 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.

03

Xbox One X GPU— who makes it?

This is a product of AMD, with the chip manufactured by TSMC, on a process of 16 nm.

04

Xbox One X GPU— when was it released?

It was released in November 2017.

05

Xbox One X GPU— how much power does it use?

Rated board power is 150 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.

06

Xbox One X GPU— what are its TFLOPS?

It is rated at 6 TFLOPS at half precision and 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.

07

Xbox One X GPU— does it support CUDA?

No. CUDA is NVIDIA-only, and this is a card from AMD. 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.

08

Xbox One X GPU— is it 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 411 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.

09

Xbox One X GPU— can it run a model that does not fit in its memory?

Offloading past the card's 12 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.

10

Would two Xbox One X GPU cards be twice as fast?

Pairing them buys headroom rather than pace: 24 GB to work with rather than twice the tokens per second — every figure here is for a single card.

11

Xbox One X GPU— which AI models can it run?

411 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.

12

Xbox One X GPU— what is the largest AI model it can run?

The largest model in our catalogue that fits is ERNIE-4.5-21B-A3B at 21B parameters, compressed to Q3_K_M. It generates roughly 77.0 tokens per second and needs about 10.1 GB of the card's memory.

13

Xbox One X GPU— 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 108 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.

14

Xbox One X GPU— 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 24.0 tokens per second.

15

Xbox One X GPU— can it run 13B models?

Yes. For example it runs DeepSeekMoE-16B at Q4_K_M, using about 10.0 GB of memory and generating around 86.4 tokens per second.

16

Xbox One X GPU— how much memory does it have?

This card has 12 GB of GDDR5. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 10.8 GB available for a model and its conversation.

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