Calculate the TPS of the AeroBox 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
721 models in our catalogue altogether
Largest model it holds
Baichuan 1-13B
13.3B · Q3_K_M · 4.6 tok/s
Fastest model
Gemma 3 QAT 1B
22.5 tok/s · 1B
Which AI models can run on a AeroBox 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.
351 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
22.5
tok/s
14–36 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
22.5
tok/s
14–36 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
22.5
tok/s
14–36 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
22.5
tok/s
14–36 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
22.5
tok/s
14–36 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
22.5
tok/s
14–36 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
20.9
tok/s
13–33 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
20.5
tok/s
12–33 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
20.5
tok/s
12–33 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
20.5
tok/s
12–33 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
20.5
tok/s
12–33 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
18.8
tok/s
11–30 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
18.8
tok/s
11–30 · low confidence |
LFM2-1.2B ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
18.8
tok/s
11–30 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
18.8
tok/s
11–30 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
18.8
tok/s
11–30 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
18.3
tok/s
11–29 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
18.1
tok/s
11–29 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
17.3
tok/s
10–28 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
17.3
tok/s
10–28 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
17.3
tok/s
10–28 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
17.3
tok/s
10–28 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
17.3
tok/s
10–28 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
17.3
tok/s
10–28 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
17.3
tok/s
10–28 · 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
AeroBox 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
- 68 GB/s
- Memory type
- DDR3
- Memory bus width
- 256 bit
- Memory clock
- 1.07 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
- Kryptos
- Architecture
- GCN 1.0
- Generation
- Console GPU(Chuwi)
- Foundry
- TSMC
- Process size
- 16 nm
- Released
- 13 March 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
- 935 MHz
- Boost clock
- 985 MHz
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
- 896
- Texture mapping units
- 56
- Render output units
- 16
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)
- 3.5 TFLOPS
- Single precision (FP32)
- 1.8 TFLOPS
- Double precision (FP64)
- 110.3 GFLOPS
- Pixel rate
- 16 GPixel/s
- Texture rate
- 55 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
- 289 mm × 56 mm
- Display outputs
- 1x DVI
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
- 11.1
- Vulkan
- 1.2
- OpenCL
- 1.2
- Shader model
- 5.1
Listings
Where to buy a AeroBox 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
68 GB/s
Largest model
Baichuan 1-13B
AeroBox GPU carries only 8 GB of DDR3. That limits it to the smaller end of the catalogue, and a model has to fit entirely inside before it generates anything at all. A runtime actually gets about 7.2 GB.
Memory bandwidth reaches 68 GB/s across a bus of 256 bits. 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.
That comes from a memory clock of 1.07 GHz. 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.
The practical ceiling is Baichuan 1-13B, 13.3B, compressed to Q3_K_M and generating around 4.6 tokens per second.
The chip and how it was built
AeroBox GPU is built on the graphics processor Kryptos, using the architecture GCN 1.0 from AMD, as part of the generation Console GPU(Chuwi).
The chip is manufactured by TSMC, on a process of 16 nm. 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 March 2020, roughly 6.5059983282482 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
3.5 TFLOPS
FP64
110.3 GFLOPS
On paper AeroBox GPU reaches 3.5 TFLOPS at half precision, and 1.8 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 reaches 110.3 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 a base of 935 MHz to a boost of 985 MHz. 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 896 shading units, 56 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
100 W
AeroBox 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 289 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 AeroBox 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 AeroBox 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 AeroBox 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
The table lists 351 models the card handles. The search box takes a name or a size such as 27b, which matches on parameter count.
-
02
Set the context length you will actually use
Drag the slider to the conversation length you plan to work at. The cache grows with the conversation, and against a card holding 8 GB it is often what pushes a large model over the edge.
-
03
Choose how far you will compress
By default the table picks the least-compressed copy that fits. Setting a floor removes models that only qualify through heavy compression.
-
04
Look at the range, not just the number
Speeds come with error bars for a reason. The best case here is 22.5 tok/s on Gemma 3 QAT 1B. The same card and model vary by thirty to fifty per cent between inference runtimes.
-
05
Check the memory column before committing
The fit column separates models that just fit from those with room to spare — worth checking before settling on one, against an available 8 GB.
-
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, alongside AeroBox GPU.
Answers
AeroBox GPU — common questions
AeroBox 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.
AeroBox GPU— is it 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 351 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
AeroBox GPU— can it run a model that does not fit in its memory?
Offloading past the card's 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.
Would two AeroBox GPU cards be twice as fast?
Capacity adds, throughput does not. Two of them give you 16 GB to work with rather than twice the tokens per second — every figure here is for a single card.
AeroBox GPU— which AI models can it run?
351 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.
AeroBox GPU— what is the largest AI model it can run?
The largest model in our catalogue that fits is Baichuan 1-13B at 13.3B parameters, compressed to Q3_K_M. It generates roughly 4.6 tokens per second and needs about 7.2 GB of the card's memory.
AeroBox 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 22.5 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.
AeroBox GPU— can it run 7B models?
Yes. For example it runs Gemma 4 E4B at Q5_K_M, using about 7.0 GB of memory and generating around 8.9 tokens per second.
AeroBox GPU— can it run 13B models?
Yes. For example it runs Gemma 4 12B at Q3_K_M, using about 6.5 GB of memory and generating around 5.1 tokens per second.
AeroBox GPU— how much memory does it have?
This card has 8 GB of DDR3. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 7.2 GB available for a model and its conversation.
AeroBox GPU— what is its memory bandwidth?
Memory bandwidth reaches 68 GB/s across a bus of 256 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.
AeroBox GPU— what type of memory does it use?
It uses DDR3 clocked at 1.07 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.
AeroBox GPU— who makes it?
This is a product of AMD, with the chip manufactured by TSMC, on a process of 16 nm.
AeroBox GPU— when was it released?
It was released in March 2020.
AeroBox GPU— how much power does it use?
Rated board power is 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.
AeroBox GPU— what are its TFLOPS?
It is rated at 3.5 TFLOPS at half precision and 1.8 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.
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.