Calculate the TPS of the Radeon PRO V710 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
Qwen2-57B-A14B
57B · Q3_K_M · 32.1 tok/s
Fastest model
Gemma 3 QAT 1B
167 tok/s · 1B
What AI models can a Radeon PRO V710 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.
511 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
167
tok/s
100–266 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
167
tok/s
100–266 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
167
tok/s
100–266 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
167
tok/s
100–266 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
167
tok/s
100–266 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
167
tok/s
100–266 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
154
tok/s
93–247 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
151
tok/s
91–242 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
151
tok/s
91–242 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
151
tok/s
91–242 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
151
tok/s
91–242 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
139
tok/s
83–222 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
139
tok/s
83–222 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
139
tok/s
83–222 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
139
tok/s
83–222 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
135
tok/s
81–217 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
133
tok/s
80–214 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · 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 V710 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
- 28 GB
- Memory bandwidth
- 504 GB/s
- Memory type
- GDDR6
- Memory bus width
- 224 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 32
- Architecture
- RDNA 3.0
- Generation
- Radeon Pro Navi(Navi III Series)
- Foundry
- TSMC
- Process size
- 5 nm
- Transistors
- 28.1 billion
- Transistor density
- 81,200 K/mm²
- Die size
- 346 mm²
- Package
- MCM
- Released
- 3 October 2024
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
- 1.9 GHz
- Boost clock
- 2 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
- 3,456
- Texture mapping units
- 216
- Render output units
- 96
- Ray tracing cores
- 54
- L1 cache
- 128 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)
- 55.3 TFLOPS
- Single precision (FP32)
- 27.7 TFLOPS
- Double precision (FP64)
- 864 GFLOPS
- Pixel rate
- 192 GPixel/s
- Texture rate
- 432 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)
- 158 W
- Suggested power supply
- 450 W
- Power connectors
- 1x 8-pin
- Bus interface
- PCIe 4.0 x16
- Slot width
- Single-slot
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 PRO V710
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
28 GB
Bandwidth
504 GB/s
Largest model
Qwen2-57B-A14B
The Radeon PRO V710 carries 28 GB of GDDR6, which covers the mid-sized models most people actually run — about 25.2 GB of it after the runtime and driver reserve their working space.
The memory bus moves 504 GB/s across a 224-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.
Bandwidth is clock times bus width, and this card clocks its memory at 2.25 GHz. Both halves matter, and neither is visible in a gaming benchmark.
The practical ceiling is Qwen2-57B-A14B at 57B, held at Q3_K_M and running at roughly 32.1 tokens per second.
The chip and how it was built
The Radeon PRO V710 is built on the Navi 32 graphics processor, using AMD's RDNA 3.0 architecture, as part of the Radeon Pro Navi(Navi III Series) generation.
The chip is manufactured by TSMC, on a 5 nm process, with a die measuring 346 mm², holding 28.1 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 October 2024, roughly 1 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
55.3 TFLOPS
FP64
864 GFLOPS
On paper the Radeon PRO V710 reaches 55.3 TFLOPS at half precision and 27.7 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 864 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 1.9 GHz at base to 2 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 V710 has 128 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 3,456 shading units, 216 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
158 W
The Radeon PRO V710 is rated at 158 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, and needs 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 4.0 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 PRO V710 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 PRO V710
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 V710
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 511 models this Radeon PRO V710 can run. Search by name, or by size — typing 27b matches on the parameter count even when the name never states it.
-
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 28 GB.
-
03
Set a minimum quality if you need one
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
The figures are calculated, not measured. 167 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
Compare what each model needs with the 28 GB this card provides. Tight means it works today; comfortable means it still works when the conversation grows.
-
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, and how the Radeon PRO V710 compares.
Answers
Radeon PRO V710 — common questions
Is the Radeon PRO V710 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 511 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 V710 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 28 GB figures on this page assume it.
Would two Radeon PRO V710 cards be twice as fast?
No. A second Radeon PRO V710 doubles the memory to 56 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 V710 run?
511 of the 679 open-weight language models we track fit on a Radeon PRO V710 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 V710 can run?
The largest model in our catalogue that fits on a Radeon PRO V710 is Qwen2-57B-A14B at 57B parameters, compressed to Q3_K_M. It generates roughly 32.1 tokens per second and needs about 24.6 GB of the card's memory.
How many tokens per second does a Radeon PRO V710 produce?
It depends on the model. On a Radeon PRO V710 the fastest model we track is Gemma 3 QAT 1B at about 167 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 V710 run a 7B model?
Yes. For example a Radeon PRO V710 runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 24.9 tokens per second.
Can a Radeon PRO V710 run a 13B model?
Yes. For example a Radeon PRO V710 runs DeepSeekMoE-16B at Q8_0, using about 17.5 GB of memory and generating around 57.8 tokens per second.
Can a Radeon PRO V710 run a 30B model?
Yes. For example a Radeon PRO V710 runs Nemotron 3-Nano-30B-A3B at Q5_K_M, using about 21.7 GB of memory and generating around 52.3 tokens per second.
How much memory does a Radeon PRO V710 have?
A Radeon PRO V710 has 28 GB of GDDR6 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 25.2 GB available for a model and its conversation.
What is the memory bandwidth of a Radeon PRO V710?
The Radeon PRO V710 has 504 GB/s of memory bandwidth, across a 224-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 PRO V710 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 PRO V710?
The Radeon PRO V710 is a AMD product, with the chip manufactured by TSMC, on a 5 nm process.
When was the Radeon PRO V710 released?
The Radeon PRO V710 was released in October 2024.
How much power does a Radeon PRO V710 use?
The Radeon PRO V710 has a rated board power of 158 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.
How much cache does a Radeon PRO V710 have?
The Radeon PRO V710 has 128 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 V710?
The Radeon PRO V710 is rated at 55.3 TFLOPS at half precision and 27.7 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 V710 support CUDA?
No. CUDA is NVIDIA-only, and the Radeon PRO V710 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 V710 use?
It uses PCIe 4.0 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.
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.