Calculate the TPS of the Xbox Series X 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
Largest model it holds
Ling-lite-1.5 ("Bailing")
16.8B · Q3_K_M · 29.7 tok/s
Fastest model
Gemma 3 QAT 1B
185 tok/s · 1B
What AI models can a Xbox Series X GPU run?
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.
381 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
185
tok/s
111–296 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
185
tok/s
111–296 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
185
tok/s
111–296 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
185
tok/s
111–296 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
185
tok/s
111–296 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
185
tok/s
111–296 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
173
tok/s
104–277 · low confidence |
DeepSeekMoE-16B | 16B | Jan 2024 | 8.1 GB | 4k tokens | Q3_K_M | Tight |
|
171
tok/s
103–274 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
168
tok/s
101–269 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
168
tok/s
101–269 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
168
tok/s
101–269 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
168
tok/s
101–269 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
154
tok/s
93–247 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
154
tok/s
93–247 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
154
tok/s
93–247 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
154
tok/s
93–247 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
150
tok/s
90–241 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
148
tok/s
89–237 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
85–228 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
85–228 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
85–228 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
85–228 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
85–228 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
85–228 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
142
tok/s
85–228 · low confidence |
Otter ≈ | 1.3B | May 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 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
- 10 GB
- Memory bandwidth
- 560 GB/s
- Memory type
- GDDR6
- Memory bus width
- 320 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
- Scarlett
- Architecture
- RDNA 2.0
- Generation
- Console GPU(Microsoft)
- Foundry
- TSMC
- Process size
- 7 nm
- Transistors
- 15.3 billion
- Transistor density
- 42,500 K/mm²
- Die size
- 360 mm²
- Package
- BGA-2693
- 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
- 1.83 GHz
- Boost clock
- 1.83 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
- 3,328
- Texture mapping units
- 208
- Render output units
- 64
- L2 cache
- 5 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)
- 24.3 TFLOPS
- Single precision (FP32)
- 12.2 TFLOPS
- Double precision (FP64)
- 759.2 GFLOPS
- Pixel rate
- 117 GPixel/s
- Texture rate
- 380 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)
- 200 W
- Dimensions
- 301 mm × 151 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 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
10 GB
Bandwidth
560 GB/s
Largest model
Ling-lite-1.5 ("Bailing")
At 10 GB of GDDR6 the Xbox Series X GPU is limited to the smaller end of the catalogue. About 9 GB is actually available to a runtime, and a model has to fit entirely inside it before generating anything at all.
The memory bus moves 560 GB/s across a 320-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.
That comes from a 1.75 GHz memory clock across the bus width above. Widening the bus and raising the clock are the two levers a manufacturer has, which is why a card with unremarkable cores can still generate quickly.
Put together, the largest model that fits is Ling-lite-1.5 ("Bailing") at 16.8B, running Q3_K_M and producing around 29.7 tokens per second.
The chip and how it was built
The Xbox Series X GPU is built on the Scarlett 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 360 mm², holding 15.3 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
24.3 TFLOPS
FP64
759.2 GFLOPS
On paper the Xbox Series X GPU reaches 24.3 TFLOPS at half precision and 12.2 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 759.2 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 1.83 GHz at base to 1.83 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 5 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 3,328 shading units, 208 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
200 W
The Xbox Series X GPU is rated at 200 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 301 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 a Xbox Series X GPU can run
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 Xbox Series 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.
Step by step
How to work out the tokens per second of a Xbox Series 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.
-
01
Start with the model, not the specification
All 381 models the Xbox Series X GPU handles are already listed. The search box takes a name or a size such as 27b, which matches on parameter count.
-
02
Match the context to your work
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 10 GB.
-
03
Choose how far you will compress
Compression is what lets bigger models fit. The quality control drops any model that needs more of it than you are willing to give.
-
04
Read the speed and the range
Each speed is an estimate for a single conversation, with a range beneath it — 185 tok/s on Gemma 3 QAT 1B at the top end here. The same card and model vary by thirty to fifty per cent between inference runtimes.
-
05
Check the headroom before you decide
The fit column separates models that just fit from those with room to spare — worth checking against the card's 10 GB before settling on one.
-
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 Xbox Series X GPU sits against the alternatives.
Answers
Xbox Series X GPU — common questions
Would two Xbox Series X GPU cards be twice as fast?
Capacity adds, throughput does not. Two of them give you 20 GB to work with rather than twice the tokens per second — every figure here is for a single Xbox Series X GPU.
What AI models can a Xbox Series X GPU run?
381 of the 679 open-weight language models we track fit on a Xbox Series X 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 Xbox Series X GPU can run?
The largest model in our catalogue that fits on a Xbox Series X GPU is Ling-lite-1.5 ("Bailing") at 16.8B parameters, compressed to Q3_K_M. It generates roughly 29.7 tokens per second and needs about 8.9 GB of the card's memory.
How many tokens per second does a Xbox Series X GPU produce?
It depends on the model. On a Xbox Series X GPU the fastest model we track is Gemma 3 QAT 1B at about 185 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 Xbox Series X GPU run a 7B model?
Yes. For example a Xbox Series X GPU runs DeepSeek Coder 6.7B at Q4_K_M, using about 8.3 GB of memory and generating around 63.8 tokens per second.
Can a Xbox Series X GPU run a 13B model?
Yes. For example a Xbox Series X GPU runs DeepSeekMoE-16B at Q3_K_M, using about 8.1 GB of memory and generating around 173 tokens per second.
How much memory does a Xbox Series X GPU have?
A Xbox Series X GPU has 10 GB of GDDR6 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 9 GB available for a model and its conversation.
What is the memory bandwidth of a Xbox Series X GPU?
The Xbox Series X GPU has 560 GB/s of memory bandwidth, across a 320-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 Xbox Series X 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 Xbox Series X GPU?
The Xbox Series X GPU is a AMD product, with the chip manufactured by TSMC, on a 7 nm process.
When was the Xbox Series X GPU released?
The Xbox Series X GPU was released in November 2020.
How much power does a Xbox Series X GPU use?
The Xbox Series X GPU has a rated board power of 200 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 Xbox Series X GPU have?
and 5 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 Xbox Series X GPU?
The Xbox Series X GPU is rated at 24.3 TFLOPS at half precision and 12.2 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 Xbox Series X GPU support CUDA?
No. CUDA is NVIDIA-only, and the Xbox Series X 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 Xbox Series X GPU good for running local AI models?
Its memory limits it to smaller models and its bandwidth gives usable, if unspectacular, generation speeds. In total it runs 381 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Can a Xbox Series X GPU run a model that does not fit in its memory?
Offloading past the card's 10 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.
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.