Calculate the TPS of the Radeon RX 7900 GRE on local AI models

AMD 16 GB GDDR6 576 GB/s July 2023

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

432 models it can run

679 models in our catalogue altogether

Largest model it holds

Nemotron 3-Nano-30B-A3B

31.6B · Q3_K_M · 90.3 tok/s

Fastest model

Gemma 3 QAT 1B

190 tok/s · 1B

Which AI models can run on a Radeon RX 7900 GRE?

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
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 RX 7900 GRE 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
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 31
Architecture
RDNA 3.0
Generation
Navi III(RX 7000)
Foundry
TSMC
Process size
5 nm
Transistors
57.7 billion
Transistor density
109,100 K/mm²
Die size
529 mm²
Package
MCM
Released
27 July 2023

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
1.29 GHz
Boost clock
2.25 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
5,120
Texture mapping units
320
Render output units
160
Ray tracing cores
80
L1 cache
250 KB
L2 cache
6 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)
92 TFLOPS
Single precision (FP32)
46 TFLOPS
Double precision (FP64)
1.4 TFLOPS
Pixel rate
359 GPixel/s
Texture rate
718 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)
260 W
Suggested power supply
600 W
Power connectors
2x 8-pin
Bus interface
PCIe 4.0 x16
Slot width
Dual-slot
Dimensions
276 mm × 51 mm
Display outputs
1x HDMI 2.1a, 2x DisplayPort 2.1, 1x USB Type-C

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 RX 7900 GRE

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

16 GB

Bandwidth

576 GB/s

Largest model

Nemotron 3-Nano-30B-A3B

Radeon RX 7900 GRE carries 16 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 14.4 GB.

Memory bandwidth reaches 576 GB/s across a bus of 256 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.

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.

In practice that combination tops out at Nemotron 3-Nano-30B-A3B, 31.6B, compressed to Q3_K_M and generating around 90.3 tokens per second.

The chip and how it was built

Radeon RX 7900 GRE is built on the graphics processor Navi 31, using the architecture RDNA 3.0 from AMD, as part of the generation Navi III(RX 7000).

The chip is manufactured by TSMC, on a process of 5 nm, with a die measuring 529 mm², holding 57.7 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 July 2023, roughly 3.0133869722727 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

92 TFLOPS

FP64

1.4 TFLOPS

On paper Radeon RX 7900 GRE reaches 92 TFLOPS at half precision, and 46 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 1.4 TFLOPS. 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 1.29 GHz to a boost of 2.25 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 7900 GRE has an L1 cache of 250 KB, backed by an L2 cache of 6 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 5,120 shading units, 320 texture mapping units, and 160 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

260 W

Radeon RX 7900 GRE is rated at 260 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 276 mm long, and needs 2x 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 7900 GRE

The biggest open-weight models that fit on this card, newest first. Each is shown at the best compression the card can hold.

  1. 01 North Mini Code 30B · Q3_K_M · Jun 2026 95.1 tok/s
  2. 02 Qwen 3.6-27B 27B · Q3_K_M · Apr 2026 19.0 tok/s
  3. 03 Qwen3.5-27B 27B · Q3_K_M · Feb 2026 19.0 tok/s
  4. 04 Nemotron 3-Nano-30B-A3B 31.6B · Q3_K_M · Dec 2025 90.3 tok/s
  5. 05 Nomos 1 30B · Q3_K_M · Dec 2025 95.1 tok/s
  6. 06 C2S-Scale 27B · Q3_K_M · Oct 2025 19.0 tok/s
  7. 07 Gemma-SEA-LION-v4-27B-IT 27B · Q3_K_M · Aug 2025 19.0 tok/s
  8. 08 ERNIE-4.5-VL-28B-A3B 28B · Q3_K_M · Jun 2025 102 tok/s
  9. 09 Qwen3-30B-A3B 30B · Q3_K_M · Apr 2025 95.1 tok/s
  10. 10 Gemma 3 QAT 27B 27B · Q3_K_M · Apr 2025 19.0 tok/s

The fastest AI models on a Radeon RX 7900 GRE

Where this card produces tokens quickest. Smaller models dominate here, because generating each token means reading the whole model out of memory once.

  1. 01 Gemma 3 QAT 1B 1B · Q8_0 · 1.8 GB 190 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 190 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 190 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 190 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 190 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 190 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 176 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 173 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 173 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 173 tok/s

Step by step

How to work out the tokens per second of a Radeon RX 7900 GRE

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.

  1. 01

    Search for the model you want

    The table lists 432 models this card runs. Search narrows the list by name or by size.

  2. 02

    Match the context to your work

    Set the context to your real working length. Short questions cost almost nothing, but a long document can consume a large share of 16 GB so the setting is worth getting right.

  3. 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.

  4. 04

    Read the speed and the range

    Speeds come with error bars for a reason. The best case here is 190 tok/s on Gemma 3 QAT 1B. The same card and model vary by thirty to fifty per cent between inference runtimes.

  5. 05

    Check the headroom before you decide

    Tight means it works today; comfortable means it still works when the conversation grows. Compare what each model needs against an available 16 GB.

  6. 06

    Check the same model from the other side

    Each model page repeats this calculation for the whole catalogue. Worth a look before deciding: it shows what else runs the same model, alongside Radeon RX 7900 GRE.

Answers

Radeon RX 7900 GRE — common questions

01

Radeon RX 7900 GRE— when was it released?

It was released in July 2023.

02

Radeon RX 7900 GRE— how much power does it use?

Rated board power is 260 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.

03

Radeon RX 7900 GRE— how much cache does it have?

The L1 cache is 250 KB, and the L2 cache is 6 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.

04

Radeon RX 7900 GRE— what are its TFLOPS?

It is rated at 92 TFLOPS at half precision and 46 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.

05

Radeon RX 7900 GRE— 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.

06

Radeon RX 7900 GRE— 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.

07

Radeon RX 7900 GRE— 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 432 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.

08

Radeon RX 7900 GRE— can it run a model that does not fit in its memory?

Only partly. Layers beyond the card's 16 GB drags the whole thing down, and none of the figures on this page assume it.

09

Would two Radeon RX 7900 GRE cards be twice as fast?

No. A second card 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.

10

Radeon RX 7900 GRE— which AI models can it run?

432 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.

11

Radeon RX 7900 GRE— what is the largest AI model it can run?

The largest model in our catalogue that fits is Nemotron 3-Nano-30B-A3B at 31.6B parameters, compressed to Q3_K_M. It generates roughly 90.3 tokens per second and needs about 14.4 GB of the card's memory.

12

Radeon RX 7900 GRE— 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 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.

13

Radeon RX 7900 GRE— can it run 7B models?

Yes. For example it runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 28.4 tokens per second.

14

Radeon RX 7900 GRE— can it run 13B models?

Yes. For example it runs DeepSeekMoE-16B at Q6_K, using about 13.7 GB of memory and generating around 96.0 tokens per second.

15

Radeon RX 7900 GRE— can it run 30B models?

Yes. For example it runs ERNIE-4.5-VL-28B-A3B at Q3_K_M, using about 12.9 GB of memory and generating around 102 tokens per second.

16

Radeon RX 7900 GRE— how much memory does it have?

This card has 16 GB of GDDR6. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 14.4 GB available for a model and its conversation.

17

Radeon RX 7900 GRE— what is its memory bandwidth?

Memory bandwidth reaches 576 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.

18

Radeon RX 7900 GRE— 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.

19

Radeon RX 7900 GRE— who makes it?

This is a product of AMD, with the chip manufactured by TSMC, on a process of 5 nm.

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.

All GPUs