Calculate the TPS of the Radeon RX 6750 XT 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
ERNIE-4.5-21B-A3B
21B · Q3_K_M · 102 tok/s
Fastest model
Gemma 3 QAT 1B
143 tok/s · 1B
Which AI models can run on a Radeon RX 6750 XT?
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.
396 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
143
tok/s
86–228 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
143
tok/s
86–228 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
143
tok/s
86–228 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
143
tok/s
86–228 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
143
tok/s
86–228 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
143
tok/s
86–228 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
132
tok/s
79–211 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
130
tok/s
78–208 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
130
tok/s
78–208 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
130
tok/s
78–208 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
130
tok/s
78–208 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
119
tok/s
71–190 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
119
tok/s
71–190 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
119
tok/s
71–190 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
119
tok/s
71–190 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
116
tok/s
70–186 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
114
tok/s
69–183 · low confidence |
DeepSeekMoE-16B | 16B | Jan 2024 | 10.0 GB | 4k tokens | Q4_K_M | Tight |
|
114
tok/s
69–183 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
66–176 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
66–176 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
66–176 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
66–176 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
66–176 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
66–176 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
66–176 · 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
Radeon RX 6750 XT 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
- 12 GB
- Memory bandwidth
- 432 GB/s
- Memory type
- GDDR6
- Memory bus width
- 192 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 22
- Architecture
- RDNA 2.0
- Generation
- Navi II(RX 6000)
- Foundry
- TSMC
- Process size
- 7 nm
- Transistors
- 17.2 billion
- Transistor density
- 51,300 K/mm²
- Die size
- 335 mm²
- Package
- BGA-1701
- Released
- 3 March 2022
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
- 2.15 GHz
- Boost clock
- 2.6 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
- 2,560
- Texture mapping units
- 160
- Render output units
- 64
- Ray tracing cores
- 40
- L1 cache
- 128 KB
- L2 cache
- 3 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)
- 26.6 TFLOPS
- Single precision (FP32)
- 13.3 TFLOPS
- Double precision (FP64)
- 832 GFLOPS
- Pixel rate
- 166 GPixel/s
- Texture rate
- 416 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 4.0 x16
- Slot width
- Dual-slot
- Dimensions
- 267 mm × 40 mm
- Display outputs
- 1x HDMI 2.1, 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
- 12.2
- OpenGL
- 4.6
- Vulkan
- 1.4
- OpenCL
- 2.1
- Shader model
- 6.8
Listings
Where to buy a Radeon RX 6750 XT
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
12 GB
Bandwidth
432 GB/s
Largest model
ERNIE-4.5-21B-A3B
Radeon RX 6750 XT carries 12 GB of GDDR6. That reaches comfortably into small and mid-sized models, though the largest stay out of reach without splitting them. Driver overhead leaves roughly 10.8 GB.
Memory bandwidth reaches 432 GB/s across a bus of 192 bits. That is the number governing generation speed — arithmetic per byte read is small enough that the bus, not the cores, is what everything waits on.
That comes from a memory clock of 2.25 GHz. It is why core counts predict generation speed so poorly.
The practical ceiling is ERNIE-4.5-21B-A3B, 21B, compressed to Q3_K_M and generating around 102 tokens per second.
The chip and how it was built
Radeon RX 6750 XT is built on the graphics processor Navi 22, using the architecture RDNA 2.0 from AMD, as part of the generation Navi II(RX 6000).
The chip is manufactured by TSMC, on a process of 7 nm, with a die measuring 335 mm², holding 17.2 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 March 2022, roughly 4.4133873862932 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
26.6 TFLOPS
FP64
832 GFLOPS
On paper Radeon RX 6750 XT reaches 26.6 TFLOPS at half precision, and 13.3 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 832 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 2.15 GHz to a boost of 2.6 GHz. 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
Radeon RX 6750 XT has an L1 cache of 128 KB, backed by an L2 cache of 3 MB. 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 2,560 shading units, 160 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
250 W
Radeon RX 6750 XT is rated at 250 W, and the suggested system power supply is 600 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.
The board occupies dual-slot, measuring 267 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 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 that run on a Radeon RX 6750 XT
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 RX 6750 XT
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 RX 6750 XT
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
Search for the model you want
The table lists 396 models this card runs. Search narrows the list by name or by size.
-
02
Decide how long your conversations run
Longer conversations cost memory on top of the weights. Against 12 GB so the setting is worth getting right.
-
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
Look at the range, not just the number
Speeds come with error bars for a reason. The best case here is 143 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
Tight means it works today; comfortable means it still works when the conversation grows. Compare what each model needs against an available 12 GB.
-
06
Check the same model from the other side
Following a model through to its own page lists all the hardware that can run it, so you can see how it compares against Radeon RX 6750 XT.
Answers
Radeon RX 6750 XT — common questions
Radeon RX 6750 XT— can it run 13B models?
Yes. For example it runs DeepSeekMoE-16B at Q4_K_M, using about 10.0 GB of memory and generating around 114 tokens per second.
Radeon RX 6750 XT— how much memory does it have?
This card has 12 GB of GDDR6. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 10.8 GB available for a model and its conversation.
Radeon RX 6750 XT— what is its memory bandwidth?
Memory bandwidth reaches 432 GB/s across a bus of 192 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.
Radeon RX 6750 XT— what type of memory does it 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.
Radeon RX 6750 XT— who makes it?
This is a product of AMD, with the chip manufactured by TSMC, on a process of 7 nm.
Radeon RX 6750 XT— when was it released?
It was released in March 2022.
Radeon RX 6750 XT— how much power does it use?
Rated board power is 250 W, and the suggested system power supply is 600 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.
Radeon RX 6750 XT— how much cache does it have?
The L1 cache is 128 KB, and the L2 cache is 3 MB. 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.
Radeon RX 6750 XT— what are its TFLOPS?
It is rated at 26.6 TFLOPS at half precision and 13.3 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.
Radeon RX 6750 XT— 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.
Radeon RX 6750 XT— what bus interface does it 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.
Radeon RX 6750 XT— is it good for running local AI models?
Its memory covers small and mid-sized models, though the largest are out of reach and its bandwidth gives usable, if unspectacular, generation speeds. In total it runs 396 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Radeon RX 6750 XT— can it run a model that does not fit in its memory?
Offloading past the card's 12 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 Radeon RX 6750 XT cards be twice as fast?
No. A second card doubles the memory to 24 GB to work with rather than twice the tokens per second — every figure here is for a single card.
Radeon RX 6750 XT— which AI models can it run?
396 of the 679 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.
Radeon RX 6750 XT— what is the largest AI model it can run?
The largest model in our catalogue that fits is ERNIE-4.5-21B-A3B at 21B parameters, compressed to Q3_K_M. It generates roughly 102 tokens per second and needs about 10.1 GB of the card's memory.
Radeon RX 6750 XT— 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 143 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.
Radeon RX 6750 XT— can it run 7B models?
Yes. For example it runs DeepSeek Coder 6.7B at Q6_K, using about 9.9 GB of memory and generating around 31.0 tokens per second.
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.