Calculate the TPS of the Radeon Pro Duo Polaris 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 · 35.1 tok/s
Fastest model
Gemma 3 QAT 1B
74.0 tok/s · 1B
Which AI models can run on a Radeon Pro Duo Polaris?
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 | ||||||
|---|---|---|---|---|---|---|---|
|
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
Radeon Pro Duo Polaris 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
- 224 GB/s
- Memory type
- GDDR5
- Memory bus width
- 256 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
- Ellesmere
- Architecture
- GCN 4.0
- Generation
- Radeon Pro GCN
- Foundry
- GlobalFoundries
- Process size
- 14 nm
- Transistors
- 5.7 billion
- Transistor density
- 24,600 K/mm²
- Die size
- 232 mm²
- Package
- BGA-1401
- Released
- 24 April 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
- 1.24 GHz
- Boost clock
- 1.24 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
- 2,304
- Texture mapping units
- 144
- Render output units
- 32
- L1 cache
- 16 KB
- 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)
- 5.7 TFLOPS
- Single precision (FP32)
- 5.7 TFLOPS
- Double precision (FP64)
- 358 GFLOPS
- Pixel rate
- 40 GPixel/s
- Texture rate
- 179 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)
- 250 W
- Suggested power supply
- 600 W
- Power connectors
- 1x 6-pin + 1x 8-pin
- Bus interface
- PCIe 3.0 x16
- Slot width
- Dual-slot
- Dimensions
- 305 mm
- Display outputs
- 1x HDMI 2.0b, 3x DisplayPort 1.4a
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
- OpenGL
- 4.6
- Vulkan
- 1.3
- OpenCL
- 2.1
- Shader model
- 6.7
Listings
Where to buy a Radeon Pro Duo Polaris
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
What the memory subsystem means for AI
Memory
16 GB
Bandwidth
224 GB/s
Largest model
Nemotron 3-Nano-30B-A3B
16 GB of GDDR5 puts the Radeon Pro Duo Polaris 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 224 GB/s across a 256-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.
In practice that combination tops out at Nemotron 3-Nano-30B-A3B — 31.6B, compressed to Q3_K_M, generating around 35.1 tokens per second.
The chip and how it was built
The Radeon Pro Duo Polaris is built on the Ellesmere graphics processor, using AMD's GCN 4.0 architecture, as part of the Radeon Pro GCN generation.
The chip is manufactured by GlobalFoundries, on a 14 nm process, with a die measuring 232 mm², holding 5.7 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 April 2017, roughly 9 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
5.7 TFLOPS
FP64
358 GFLOPS
On paper the Radeon Pro Duo Polaris reaches 5.7 TFLOPS at half precision and 5.7 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 358 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 1.24 GHz at base to 1.24 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 Radeon Pro Duo Polaris has 16 KB of L1 cache, 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 2,304 shading units, 144 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
250 W
The Radeon Pro Duo Polaris is rated at 250 W, with a 600 W power supply suggested for the whole system. 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.
The board occupies a dual-slot, measuring 305 mm long, and needs 1x 6-pin + 1x 8-pin. 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.
It connects over PCIe 3.0 x16. The interface governs how quickly a model is loaded from disk into the card, not how fast it runs once there, so a narrower link costs a few seconds at startup and nothing thereafter.
The extremes
The largest AI models that run on a Radeon Pro Duo Polaris
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 Radeon Pro Duo Polaris
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 Radeon Pro Duo Polaris
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
All 432 models the Radeon Pro Duo Polaris handles are already listed. The search box takes a name or a size such as 27b, which matches on parameter count.
-
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
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.
-
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.
-
05
Read the fit verdict last
The fit column separates models that just fit from those with room to spare — worth checking against the card's 16 GB before settling on one.
-
06
Cross-check against other hardware
Each model page repeats this calculation for the whole catalogue. Worth a look before deciding: it shows what else runs the same model, and how the Radeon Pro Duo Polaris compares.
Answers
Radeon Pro Duo Polaris — common questions
What type of memory does a Radeon Pro Duo Polaris use?
It uses GDDR5 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 Radeon Pro Duo Polaris?
The Radeon Pro Duo Polaris is a AMD product, with the chip manufactured by GlobalFoundries, on a 14 nm process.
When was the Radeon Pro Duo Polaris released?
The Radeon Pro Duo Polaris was released in April 2017.
How much power does a Radeon Pro Duo Polaris use?
The Radeon Pro Duo Polaris has a rated board power of 250 W, and a 600 W system power supply is suggested. 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 Radeon Pro Duo Polaris have?
The Radeon Pro Duo Polaris has 16 KB of L1 cache, 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.
What are the TFLOPS of a Radeon Pro Duo Polaris?
The Radeon Pro Duo Polaris is rated at 5.7 TFLOPS at half precision and 5.7 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 Radeon Pro Duo Polaris support CUDA?
No. CUDA is NVIDIA-only, and the Radeon Pro Duo Polaris 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.
What bus interface does the Radeon Pro Duo Polaris use?
It uses PCIe 3.0 x16. This governs how fast a model is loaded onto the card rather than how fast it runs once loaded, so it costs a few seconds at startup and nothing during generation.
Is the Radeon Pro Duo Polaris 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 Radeon Pro Duo Polaris run a model that does not fit in its memory?
It can be split, with the overflow held in system memory — but that part drags the whole thing down, and none of the 16 GB figures on this page assume it.
Would two Radeon Pro Duo Polaris cards be twice as fast?
No. A second Radeon Pro Duo Polaris doubles the memory to 32 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.
What AI models can a Radeon Pro Duo Polaris run?
432 of the 679 open-weight language models we track fit on a Radeon Pro Duo Polaris 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 Radeon Pro Duo Polaris can run?
The largest model in our catalogue that fits on a Radeon Pro Duo Polaris is Nemotron 3-Nano-30B-A3B at 31.6B parameters, compressed to Q3_K_M. It generates roughly 35.1 tokens per second and needs about 14.4 GB of the card's memory.
How many tokens per second does a Radeon Pro Duo Polaris produce?
It depends on the model. On a Radeon Pro Duo Polaris 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.
Can a Radeon Pro Duo Polaris run a 7B model?
Yes. For example a Radeon Pro Duo Polaris runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 11.0 tokens per second.
Can a Radeon Pro Duo Polaris run a 13B model?
Yes. For example a Radeon Pro Duo Polaris runs DeepSeekMoE-16B at Q6_K, using about 13.7 GB of memory and generating around 37.3 tokens per second.
Can a Radeon Pro Duo Polaris run a 30B model?
Yes. For example a Radeon Pro Duo Polaris runs ERNIE-4.5-VL-28B-A3B at Q3_K_M, using about 12.9 GB of memory and generating around 39.6 tokens per second.
How much memory does a Radeon Pro Duo Polaris have?
A Radeon Pro Duo Polaris has 16 GB of GDDR5 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 Radeon Pro Duo Polaris?
The Radeon Pro Duo Polaris has 224 GB/s of memory bandwidth, across a 256-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.
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.