Calculate the TPS of the GeForce RTX 3060 Ti GDDR6X 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
Baichuan 1-13B
13.3B · Q3_K_M · 52.4 tok/s
Fastest model
Gemma 3 QAT 1B
258 tok/s · 1B
Which AI models can run on a GeForce RTX 3060 Ti GDDR6X?
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.
337 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
258
tok/s
219–309 |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
258
tok/s
219–309 |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
258
tok/s
155–412 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
258
tok/s
155–412 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
258
tok/s
155–412 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
258
tok/s
155–412 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
239
tok/s
143–382 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
234
tok/s
141–375 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
234
tok/s
141–375 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
234
tok/s
141–375 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
234
tok/s
141–375 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
215
tok/s
129–344 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
215
tok/s
129–344 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
215
tok/s
129–344 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
215
tok/s
129–344 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
209
tok/s
178–251 |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
207
tok/s
124–330 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
198
tok/s
119–317 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
198
tok/s
119–317 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
198
tok/s
119–317 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
198
tok/s
119–317 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
198
tok/s
119–317 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
198
tok/s
119–317 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
198
tok/s
119–317 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
198
tok/s
119–317 · 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
GeForce RTX 3060 Ti GDDR6X 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
- 8 GB
- Memory bandwidth
- 608 GB/s
- Memory type
- GDDR6X
- Memory bus width
- 256 bit
- Memory clock
- 1.19 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
- GA104
- Architecture
- Ampere
- Generation
- GeForce 30
- Foundry
- Samsung
- Process size
- 8 nm
- Transistors
- 17.4 billion
- Transistor density
- 44,400 K/mm²
- Die size
- 392 mm²
- Package
- BGA-2713
- Released
- 19 October 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
- 1.41 GHz
- Boost clock
- 1.67 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
- 4,864
- Texture mapping units
- 152
- Render output units
- 80
- Streaming multiprocessors
- 38
- Tensor cores
- 152
- Ray tracing cores
- 38
- L1 cache
- 128 KB
- L2 cache
- 4 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)
- 16.2 TFLOPS
- Single precision (FP32)
- 16.2 TFLOPS
- Double precision (FP64)
- 253.1 GFLOPS
- Pixel rate
- 133 GPixel/s
- Texture rate
- 253 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)
- 225 W
- Suggested power supply
- 550 W
- Power connectors
- 1x 12-pin
- Bus interface
- PCIe 4.0 x16
- Slot width
- Dual-slot
- Dimensions
- 242 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.
- CUDA compute capability
- 8.6
- DirectX
- 12.2
- OpenGL
- 4.6
- Vulkan
- 1.4
- OpenCL
- 3.0
- Shader model
- 6.8
Listings
Where to buy a GeForce RTX 3060 Ti GDDR6X
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
8 GB
Bandwidth
608 GB/s
Largest model
Baichuan 1-13B
At 8 GB of GDDR6X the GeForce RTX 3060 Ti GDDR6X is limited to the smaller end of the catalogue. About 7.2 GB is actually available to a runtime, and a model has to fit entirely inside it before generating anything at all.
The memory bus moves 608 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.
That comes from a 1.19 GHz memory clock across the bus width above. Widening the bus and raising the clock are the two levers a manufacturer has, which is why a card with unremarkable cores can still generate quickly.
The practical ceiling is Baichuan 1-13B at 13.3B, held at Q3_K_M and running at roughly 52.4 tokens per second.
The chip and how it was built
The GeForce RTX 3060 Ti GDDR6X is built on the GA104 graphics processor, using NVIDIA's Ampere architecture, as part of the GeForce 30 generation.
The chip is manufactured by Samsung, on a 8 nm process, with a die measuring 392 mm², holding 17.4 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 2022, roughly 3 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
16.2 TFLOPS
FP64
253.1 GFLOPS
Tensor cores
152
On paper the GeForce RTX 3060 Ti GDDR6X reaches 16.2 TFLOPS at half precision and 16.2 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 253.1 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.
The card carries 152 tensor cores across 38 streaming multiprocessors. These accelerate the matrix arithmetic at the heart of a transformer, and they are what make prompt processing — reading a long document before answering — dramatically faster than it would otherwise be.
Clocks run from 1.41 GHz at base to 1.67 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 GeForce RTX 3060 Ti GDDR6X has 128 KB of L1 cache, backed by 4 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 4,864 shading units, 152 texture mapping units, and 80 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
225 W
The GeForce RTX 3060 Ti GDDR6X is rated at 225 W, with a 550 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 242 mm long, and needs 1x 12-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 GeForce RTX 3060 Ti GDDR6X
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 GeForce RTX 3060 Ti GDDR6X
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 GeForce RTX 3060 Ti GDDR6X
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
Start with the model, not the specification
The table lists 337 models this GeForce RTX 3060 Ti GDDR6X can run. Search by name, or by size — typing 27b matches on the parameter count even when the name never states it.
-
02
Set the context length you will actually use
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 8 GB.
-
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 258 tok/s on Gemma 3 QAT 1B, and which inference software you use moves that by thirty to fifty per cent.
-
05
Check the headroom before you decide
A tight fit runs but leaves no room to raise the context later; comfortable has headroom. The memory column shows what each model needs against the 8 GB available.
-
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, and how the GeForce RTX 3060 Ti GDDR6X compares.
Answers
GeForce RTX 3060 Ti GDDR6X — common questions
How many tokens per second does a GeForce RTX 3060 Ti GDDR6X produce?
It depends on the model. On a GeForce RTX 3060 Ti GDDR6X the fastest model we track is Gemma 3 QAT 1B at about 258 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 GeForce RTX 3060 Ti GDDR6X run a 7B model?
Yes. For example a GeForce RTX 3060 Ti GDDR6X runs MetaMath 7B (LLaMa finetune) at Q4_K_M, using about 6.5 GB of memory and generating around 85.0 tokens per second.
Can a GeForce RTX 3060 Ti GDDR6X run a 13B model?
Yes. For example a GeForce RTX 3060 Ti GDDR6X runs Gemma 4 12B at Q3_K_M, using about 6.5 GB of memory and generating around 58.2 tokens per second.
How much memory does a GeForce RTX 3060 Ti GDDR6X have?
A GeForce RTX 3060 Ti GDDR6X has 8 GB of GDDR6X memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 7.2 GB available for a model and its conversation.
What is the memory bandwidth of a GeForce RTX 3060 Ti GDDR6X?
The GeForce RTX 3060 Ti GDDR6X has 608 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 GeForce RTX 3060 Ti GDDR6X use?
It uses GDDR6X clocked at 1.19 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 GeForce RTX 3060 Ti GDDR6X?
The GeForce RTX 3060 Ti GDDR6X is a NVIDIA product, with the chip manufactured by Samsung, on a 8 nm process.
When was the GeForce RTX 3060 Ti GDDR6X released?
The GeForce RTX 3060 Ti GDDR6X was released in October 2022.
How much power does a GeForce RTX 3060 Ti GDDR6X use?
The GeForce RTX 3060 Ti GDDR6X has a rated board power of 225 W, and a 550 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 GeForce RTX 3060 Ti GDDR6X have?
The GeForce RTX 3060 Ti GDDR6X has 128 KB of L1 cache, and 4 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 GeForce RTX 3060 Ti GDDR6X?
The GeForce RTX 3060 Ti GDDR6X is rated at 16.2 TFLOPS at half precision and 16.2 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.
How many tensor cores does a GeForce RTX 3060 Ti GDDR6X have?
The GeForce RTX 3060 Ti GDDR6X has 152 tensor cores across 38 streaming multiprocessors. They accelerate the matrix arithmetic a transformer is built from, which mainly speeds up processing a long prompt rather than producing the reply.
Does the GeForce RTX 3060 Ti GDDR6X support CUDA?
Yes. The GeForce RTX 3060 Ti GDDR6X reports CUDA compute capability 8.6. Capability 7.0 and above has tensor cores, which modern inference software uses; below that it falls back to slower code paths for quantised models.
What bus interface does the GeForce RTX 3060 Ti GDDR6X 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.
Is the GeForce RTX 3060 Ti GDDR6X good for running local AI models?
Its memory limits it to smaller models and its bandwidth gives usable, if unspectacular, generation speeds. In total it runs 337 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Can a GeForce RTX 3060 Ti GDDR6X run a model that does not fit in its memory?
Only partly. Layers beyond the 8 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 GeForce RTX 3060 Ti GDDR6X cards be twice as fast?
Pairing GeForce RTX 3060 Ti GDDR6X cards buys headroom rather than pace: 16 GB of combined memory, at roughly the same generation speed as one.
What AI models can a GeForce RTX 3060 Ti GDDR6X run?
337 of the 679 open-weight language models we track fit on a GeForce RTX 3060 Ti GDDR6X 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 GeForce RTX 3060 Ti GDDR6X can run?
The largest model in our catalogue that fits on a GeForce RTX 3060 Ti GDDR6X is Baichuan 1-13B at 13.3B parameters, compressed to Q3_K_M. It generates roughly 52.4 tokens per second and needs about 7.2 GB of the card's memory.
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.