Calculate the TPS of the Radeon AI PRO 9600D 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
Phi-3.5-MoE
60.8B · Q3_K_M · 46.9 tok/s
Fastest model
Gemma 3 QAT 1B
190 tok/s · 1B
What AI models can a Radeon AI PRO 9600D 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.
513 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
190
tok/s
114–304 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
190
tok/s
114–304 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
190
tok/s
114–304 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
190
tok/s
114–304 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
190
tok/s
114–304 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
190
tok/s
114–304 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
176
tok/s
106–282 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
173
tok/s
104–277 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
173
tok/s
104–277 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
173
tok/s
104–277 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
173
tok/s
104–277 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
159
tok/s
95–254 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
159
tok/s
95–254 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
159
tok/s
95–254 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
159
tok/s
95–254 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
155
tok/s
93–248 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
153
tok/s
92–244 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
146
tok/s
88–234 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
146
tok/s
88–234 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
146
tok/s
88–234 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
146
tok/s
88–234 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
146
tok/s
88–234 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
146
tok/s
88–234 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
146
tok/s
88–234 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
146
tok/s
88–234 · 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 AI PRO 9600D 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
- 32 GB
- Memory bandwidth
- 576 GB/s
- Memory type
- GDDR6
- Memory bus width
- 256 bit
- Memory clock
- 2.25 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
- Navi 48
- Architecture
- RDNA 4.0
- Generation
- Radeon Pro Navi(Navi IV Series)
- Foundry
- TSMC
- Process size
- 4 nm
- Transistors
- 53.9 billion
- Transistor density
- 151,000 K/mm²
- Die size
- 357 mm²
- Package
- Monolithic
- Released
- 11 December 2025
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
- 1.08 GHz
- Boost clock
- 2.02 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
- 3,072
- Texture mapping units
- 192
- Render output units
- 96
- Ray tracing cores
- 48
- L2 cache
- 8 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)
- 49.6 TFLOPS
- Single precision (FP32)
- 24.8 TFLOPS
- Double precision (FP64)
- 775.7 GFLOPS
- Pixel rate
- 194 GPixel/s
- Texture rate
- 388 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
- Suggested power supply
- 450 W
- Power connectors
- 1x 16-pin
- Bus interface
- PCIe 5.0 x16
- Slot width
- Single-slot
- Dimensions
- 241 mm × 19 mm
- Display outputs
- 1x DisplayPort 2.1a
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
- 1.4
- OpenCL
- 2.2
- Shader model
- 6.8
Listings
Where to buy a Radeon AI PRO 9600D
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
32 GB
Bandwidth
576 GB/s
Largest model
Phi-3.5-MoE
The Radeon AI PRO 9600D carries 32 GB of GDDR6, which covers the mid-sized models most people actually run — about 28.8 GB of it after the runtime and driver reserve their working space.
The memory bus moves 576 GB/s across a 256-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.
The figure is the memory clock — 2.25 GHz here — multiplied by the bus width. It is why core counts predict generation speed so poorly.
The practical ceiling is Phi-3.5-MoE at 60.8B, held at Q3_K_M and running at roughly 46.9 tokens per second.
The chip and how it was built
The Radeon AI PRO 9600D is built on the Navi 48 graphics processor, using AMD's RDNA 4.0 architecture, as part of the Radeon Pro Navi(Navi IV Series) generation.
The chip is manufactured by TSMC, on a 4 nm process, with a die measuring 357 mm², holding 53.9 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 December 2025. 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
49.6 TFLOPS
FP64
775.7 GFLOPS
On paper the Radeon AI PRO 9600D reaches 49.6 TFLOPS at half precision and 24.8 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 is 775.7 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 1.08 GHz at base to 2.02 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 8 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 3,072 shading units, 192 texture mapping units, and 96 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
The Radeon AI PRO 9600D is rated at 150 W, with a 450 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 single-slot, measuring 241 mm long, and needs 1x 16-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 5.0 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 a Radeon AI PRO 9600D 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 Radeon AI PRO 9600D
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 AI PRO 9600D
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
Every one of the 513 models this Radeon AI PRO 9600D runs is in the table above. Search narrows it by name or by size.
-
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 on 32 GB it is often what pushes a large model over the edge.
-
03
Pin the comparison to one quality level
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
Take the range as the answer
Speeds come with error bars for a reason. The best case here is 190 tok/s on Gemma 3 QAT 1B, and which inference software you use moves that by thirty to fifty per cent.
-
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 32 GB before settling on one.
-
06
Check the same model from the other side
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 Radeon AI PRO 9600D is the right buy for it or merely a card that fits.
Answers
Radeon AI PRO 9600D — common questions
How much cache does a Radeon AI PRO 9600D have?
and 8 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 AI PRO 9600D?
The Radeon AI PRO 9600D is rated at 49.6 TFLOPS at half precision and 24.8 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.
Does the Radeon AI PRO 9600D support CUDA?
No. CUDA is NVIDIA-only, and the Radeon AI PRO 9600D 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 AI PRO 9600D use?
It uses PCIe 5.0 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 AI PRO 9600D good for running local AI models?
Its memory comfortably covers the mid-sized models most people run locally and its bandwidth gives usable, if unspectacular, generation speeds. In total it runs 513 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 AI PRO 9600D 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 32 GB figures on this page assume it.
Would two Radeon AI PRO 9600D cards be twice as fast?
Pairing Radeon AI PRO 9600D cards buys headroom rather than pace: 64 GB of combined memory, at roughly the same generation speed as one.
What AI models can a Radeon AI PRO 9600D run?
513 of the 679 open-weight language models we track fit on a Radeon AI PRO 9600D 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 AI PRO 9600D can run?
The largest model in our catalogue that fits on a Radeon AI PRO 9600D is Phi-3.5-MoE at 60.8B parameters, compressed to Q3_K_M. It generates roughly 46.9 tokens per second and needs about 27.2 GB of the card's memory.
How many tokens per second does a Radeon AI PRO 9600D produce?
It depends on the model. On a Radeon AI PRO 9600D the fastest model we track is Gemma 3 QAT 1B at about 190 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 AI PRO 9600D run a 7B model?
Yes. For example a Radeon AI PRO 9600D runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 28.4 tokens per second.
Can a Radeon AI PRO 9600D run a 13B model?
Yes. For example a Radeon AI PRO 9600D runs DeepSeekMoE-16B at Q8_0, using about 17.5 GB of memory and generating around 66.1 tokens per second.
Can a Radeon AI PRO 9600D run a 30B model?
Yes. For example a Radeon AI PRO 9600D runs ERNIE-4.5-VL-28B-A3B at Q6_K, using about 22.7 GB of memory and generating around 54.9 tokens per second.
How much memory does a Radeon AI PRO 9600D have?
A Radeon AI PRO 9600D has 32 GB of GDDR6 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 28.8 GB available for a model and its conversation.
What is the memory bandwidth of a Radeon AI PRO 9600D?
The Radeon AI PRO 9600D has 576 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.
What type of memory does a Radeon AI PRO 9600D use?
It uses GDDR6 clocked at 2.25 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 AI PRO 9600D?
The Radeon AI PRO 9600D is a AMD product, with the chip manufactured by TSMC, on a 4 nm process.
When was the Radeon AI PRO 9600D released?
The Radeon AI PRO 9600D was released in December 2025.
How much power does a Radeon AI PRO 9600D use?
The Radeon AI PRO 9600D has a rated board power of 150 W, and a 450 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.
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.