Calculate the TPS of the GeForce RTX 2070 Max-Q on local AI models

NVIDIA 8 GB GDDR6 384 GB/s January 2019

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

337 models it can run

679 models in our catalogue altogether

Largest model it holds

Baichuan 1-13B

13.3B · Q3_K_M · 33.1 tok/s

Fastest model

Gemma 3 QAT 1B

163 tok/s · 1B

Which AI models can run on a GeForce RTX 2070 Max-Q?

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
163 tok/s

138–195

Gemma 3 1B 1B Mar 2025 1.8 GB 33k tokens Q8_0 Comfortable
163 tok/s

138–195

Gemma 3 QAT 1B 1B Apr 2025 1.8 GB 33k tokens Q8_0 Comfortable
163 tok/s

98–260 · low confidence

HGRN 1B (WT 103) 1B Nov 2023 1.8 GB 131k tokens ? Q8_0 Comfortable
163 tok/s

98–260 · low confidence

LLama 3..2 Typhoon 2 1B 1B Dec 2024 1.8 GB 131k tokens ? Q8_0 Comfortable
163 tok/s

98–260 · low confidence

OLMo-1B 1B Feb 2024 1.8 GB 131k tokens ? Q8_0 Comfortable
163 tok/s

98–260 · low confidence

Pythia-1b 1B Apr 2023 1.8 GB 131k tokens ? Q8_0 Comfortable
151 tok/s

90–241 · low confidence

OpenELM-1.1B 1.1B May 2024 1.9 GB 131k tokens ? Q8_0 Comfortable
148 tok/s

89–237 · low confidence

DeciCoder-1B 1.1B Aug 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
148 tok/s

89–237 · low confidence

SantaCoder 1.1B Jan 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
148 tok/s

89–237 · low confidence

TinyLlama-1.1B (1T token checkpoint) 1.1B Oct 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
148 tok/s

89–237 · low confidence

TinyLlama-1.1B (3T token checkpoint) 1.1B Oct 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
136 tok/s

81–217 · low confidence

EXAONE 4.0 (1.2B) 1.2B Jul 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
136 tok/s

81–217 · low confidence

MinerU2.5 1.2B Sep 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
136 tok/s

81–217 · low confidence

Pleias 1.0 1.2B 1.2B Dec 2024 2.0 GB 131k tokens ? Q8_0 Comfortable
136 tok/s

81–217 · low confidence

Pleias-RAG-1B 1.2B Apr 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
132 tok/s

112–159

Llama 3.2 1B 1.2B Sep 2024 2.2 GB 131k tokens Q8_0 Comfortable
130 tok/s

78–209 · low confidence

MiniCPM-1.2B 1.2B Jun 2024 2.0 GB 131k tokens ? Q8_0 Comfortable
125 tok/s

75–200 · low confidence

DeepSeek Coder 1.3B 1.3B Jan 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
125 tok/s

75–200 · low confidence

DeepSeek-VL-1.3B 1.3B Mar 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
125 tok/s

75–200 · low confidence

DigiRL 1.3B Jun 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
125 tok/s

75–200 · low confidence

GLA Transformer 1.3B 1.3B Aug 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
125 tok/s

75–200 · low confidence

Janus 1.3B 1.3B Oct 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
125 tok/s

75–200 · low confidence

Kosmos-2.5 1.3B Aug 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
125 tok/s

75–200 · low confidence

Otter 1.3B May 2023 2.1 GB 131k tokens ? Q8_0 Comfortable
125 tok/s

75–200 · 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 2070 Max-Q 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
384 GB/s
Memory type
GDDR6
Memory bus width
256 bit
Memory clock
1.5 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
TU106
Architecture
Turing
Generation
GeForce 20 Mobile
Foundry
TSMC
Process size
12 nm
Transistors
10.8 billion
Transistor density
24,300 K/mm²
Die size
445 mm²
Package
BGA-2228
Released
29 January 2019

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
885 MHz
Boost clock
1.19 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
2,304
Texture mapping units
144
Render output units
64
Streaming multiprocessors
36
Tensor cores
288
Ray tracing cores
36
L1 cache
64 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)
10.9 TFLOPS
Single precision (FP32)
5.5 TFLOPS
Double precision (FP64)
170.6 GFLOPS
Pixel rate
76 GPixel/s
Texture rate
171 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)
90 W
Power connectors
None
Bus interface
PCIe 3.0 x16
Slot width
MXM Module

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
7.5
DirectX
12.2
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
Shader model
6.8

Listings

Where to buy a GeForce RTX 2070 Max-Q

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

What the memory subsystem means for AI

Memory

8 GB

Bandwidth

384 GB/s

Largest model

Baichuan 1-13B

GeForce RTX 2070 Max-Q carries only 8 GB of GDDR6. That limits it to the smaller end of the catalogue, and a model has to fit entirely inside before it generates anything at all. A runtime actually gets about 7.2 GB.

Memory bandwidth reaches 384 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.

The figure is the bus width multiplied by a memory clock of 1.5 GHz. It is why core counts predict generation speed so poorly.

In practice that combination tops out at Baichuan 1-13B, 13.3B, compressed to Q3_K_M and generating around 33.1 tokens per second.

The chip and how it was built

GeForce RTX 2070 Max-Q is built on the graphics processor TU106, using the architecture Turing from NVIDIA, as part of the generation GeForce 20 Mobile.

The chip is manufactured by TSMC, on a process of 12 nm, with a die measuring 445 mm², holding 10.8 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 January 2019, roughly 7.5037946040699 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

10.9 TFLOPS

FP64

170.6 GFLOPS

Tensor cores

288

On paper GeForce RTX 2070 Max-Q reaches 10.9 TFLOPS at half precision, and 5.5 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 170.6 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 288 tensor cores across 36 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 a base of 885 MHz to a boost of 1.19 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

GeForce RTX 2070 Max-Q has an L1 cache of 64 KB, backed by an L2 cache of 4 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 2,304 shading units, 144 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

90 W

GeForce RTX 2070 Max-Q is rated at 90 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 mxm module. 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 3.0 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 2070 Max-Q

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 OLMo 2 Furious 13B 13B · Q3_K_M · Dec 2024 33.8 tok/s
  2. 02 Cambrian-1-13B 13B · Q3_K_M · Jun 2024 33.8 tok/s
  3. 03 Fugaku-LLM 13B · Q3_K_M · May 2024 33.8 tok/s
  4. 04 OpenThaiGPT v1.0.0 (13B) 13.1B · Q3_K_M · Apr 2024 33.5 tok/s
  5. 05 Aya 13B · Q3_K_M · Feb 2024 33.8 tok/s
  6. 06 Elyza 13B · Q3_K_M · Dec 2023 33.8 tok/s
  7. 07 NexusRaven-V2 13B · Q3_K_M · Dec 2023 33.8 tok/s
  8. 08 Baize-v2-13B (白泽) 13B · Q3_K_M · Dec 2023 33.8 tok/s
  9. 09 Stockmark-13B 13.2B · Q3_K_M · Oct 2023 33.3 tok/s
  10. 10 Baichuan 1-13B 13.3B · Q3_K_M · Jul 2023 33.1 tok/s

The fastest AI models on a GeForce RTX 2070 Max-Q

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 163 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 163 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 163 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 163 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 163 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 163 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 151 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 148 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 148 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 148 tok/s

Step by step

How to work out the tokens per second of a GeForce RTX 2070 Max-Q

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 337 models the card handles. The search box takes a name or a size such as 27b, which matches on parameter count.

  2. 02

    Match the context to your work

    Longer conversations cost memory on top of the weights. Against 8 GB that is frequently the difference between a model fitting and not.

  3. 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.

  4. 04

    Take the range as the answer

    Speeds come with error bars for a reason. The best case here is 163 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 memory column before committing

    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 an available 8 GB.

  6. 06

    Cross-check against other hardware

    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 right buy is GeForce RTX 2070 Max-Q.

Answers

GeForce RTX 2070 Max-Q — common questions

01

GeForce RTX 2070 Max-Q— when was it released?

It was released in January 2019.

02

GeForce RTX 2070 Max-Q— how much power does it use?

Rated board power is 90 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

GeForce RTX 2070 Max-Q— how much cache does it have?

The L1 cache is 64 KB, and the L2 cache is 4 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

GeForce RTX 2070 Max-Q— what are its TFLOPS?

It is rated at 10.9 TFLOPS at half precision and 5.5 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

GeForce RTX 2070 Max-Q— how many tensor cores does it have?

It has 288 tensor cores across 36 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.

06

GeForce RTX 2070 Max-Q— does it support CUDA?

Yes. It reports CUDA compute capability 7.5. 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.

07

GeForce RTX 2070 Max-Q— what bus interface does it use?

It uses PCIe 3.0 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.

08

GeForce RTX 2070 Max-Q— is it good for running local AI models?

Its memory limits it to smaller models though its bandwidth means generation will feel slow on larger models. 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.

09

GeForce RTX 2070 Max-Q— can it run a model that does not fit in its memory?

Only partly. Layers beyond the card's 8 GB drags the whole thing down, and none of the figures on this page assume it.

10

Would two GeForce RTX 2070 Max-Q cards be twice as fast?

Pairing them buys headroom rather than pace: 16 GB of combined memory, at roughly the same generation speed as one.

11

GeForce RTX 2070 Max-Q— which AI models can it run?

337 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.

12

GeForce RTX 2070 Max-Q— what is the largest AI model it can run?

The largest model in our catalogue that fits is Baichuan 1-13B at 13.3B parameters, compressed to Q3_K_M. It generates roughly 33.1 tokens per second and needs about 7.2 GB of the card's memory.

13

GeForce RTX 2070 Max-Q— 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 163 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.

14

GeForce RTX 2070 Max-Q— can it run 7B models?

Yes. For example it runs MetaMath 7B (LLaMa finetune) at Q4_K_M, using about 6.5 GB of memory and generating around 53.6 tokens per second.

15

GeForce RTX 2070 Max-Q— can it run 13B models?

Yes. For example it runs Gemma 4 12B at Q3_K_M, using about 6.5 GB of memory and generating around 36.7 tokens per second.

16

GeForce RTX 2070 Max-Q— how much memory does it have?

This card has 8 GB of GDDR6. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 7.2 GB available for a model and its conversation.

17

GeForce RTX 2070 Max-Q— what is its memory bandwidth?

Memory bandwidth reaches 384 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

GeForce RTX 2070 Max-Q— what type of memory does it use?

It uses GDDR6 clocked at 1.5 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

GeForce RTX 2070 Max-Q— who makes it?

This is a product of NVIDIA, with the chip manufactured by TSMC, on a process of 12 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