Calculate the TPS of the GeForce GTX 1070 on local AI models

NVIDIA 8 GB GDDR5 256 GB/s June 2016

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 · 18.8 tok/s

Fastest model

Gemma 3 QAT 1B

92.3 tok/s · 1B

Which AI models can run on a GeForce GTX 1070?

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
92.3 tok/s

32–185 · low confidence

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

32–185 · low confidence

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

32–185 · low confidence

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

32–185 · low confidence

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

32–185 · low confidence

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

32–185 · low confidence

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

30–171 · low confidence

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

29–168 · low confidence

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

29–168 · low confidence

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

29–168 · low confidence

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

29–168 · low confidence

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

27–154 · low confidence

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

27–154 · low confidence

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

27–154 · low confidence

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

27–154 · low confidence

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

26–150 · low confidence

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

26–148 · low confidence

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

25–142 · low confidence

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

25–142 · low confidence

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

25–142 · low confidence

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

25–142 · low confidence

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

25–142 · low confidence

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

25–142 · low confidence

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

25–142 · low confidence

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

25–142 · 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 GTX 1070 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
256 GB/s
Memory type
GDDR5
Memory bus width
256 bit
Memory clock
2 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
GP104
Architecture
Pascal
Generation
GeForce 10
Foundry
TSMC
Process size
16 nm
Transistors
7.2 billion
Transistor density
22,900 K/mm²
Die size
314 mm²
Package
BGA-2150
Released
10 June 2016

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
1.51 GHz
Boost clock
1.68 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
1,920
Texture mapping units
120
Render output units
64
Streaming multiprocessors
15
L1 cache
48 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)
101 GFLOPS
Single precision (FP32)
6.5 TFLOPS
Double precision (FP64)
202 GFLOPS
Pixel rate
108 GPixel/s
Texture rate
202 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)
150 W
Suggested power supply
450 W
Power connectors
1x 8-pin
Bus interface
PCIe 3.0 x16
Slot width
Dual-slot
Dimensions
267 mm × 40 mm
Display outputs
1x DVI, 1x HDMI 2.0, 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
6.1
DirectX
12.1
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
Shader model
6.8

Listings

Where to buy a GeForce GTX 1070

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

Capacity and bandwidth

Memory

8 GB

Bandwidth

256 GB/s

Largest model

Baichuan 1-13B

At 8 GB of GDDR5 the GeForce GTX 1070 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.

At 256 GB/s across a 256-bit bus, bandwidth is this card's real constraint. Every token requires reading the entire model out of memory, so a large model will feel slow here even when it fits.

The figure is the memory clock — 2 GHz here — multiplied by the bus width. 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, generating around 18.8 tokens per second.

The chip and how it was built

The GeForce GTX 1070 is built on the GP104 graphics processor, using NVIDIA's Pascal architecture, as part of the GeForce 10 generation.

The chip is manufactured by TSMC, on a 16 nm process, with a die measuring 314 mm², holding 7.2 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 June 2016, roughly 10 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

101 GFLOPS

FP64

202 GFLOPS

On paper the GeForce GTX 1070 reaches 101 GFLOPS at half precision and 6.5 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 is 202 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 1.51 GHz at base to 1.68 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 GTX 1070 has 48 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 1,920 shading units, 120 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

150 W

The GeForce GTX 1070 is rated at 150 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 dual-slot, measuring 267 mm long, 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 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 GTX 1070

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 19.2 tok/s
  2. 02 Cambrian-1-13B 13B · Q3_K_M · Jun 2024 19.2 tok/s
  3. 03 Fugaku-LLM 13B · Q3_K_M · May 2024 19.2 tok/s
  4. 04 OpenThaiGPT v1.0.0 (13B) 13.1B · Q3_K_M · Apr 2024 19.0 tok/s
  5. 05 Aya 13B · Q3_K_M · Feb 2024 19.2 tok/s
  6. 06 Elyza 13B · Q3_K_M · Dec 2023 19.2 tok/s
  7. 07 NexusRaven-V2 13B · Q3_K_M · Dec 2023 19.2 tok/s
  8. 08 Baize-v2-13B (白泽) 13B · Q3_K_M · Dec 2023 19.2 tok/s
  9. 09 Stockmark-13B 13.2B · Q3_K_M · Oct 2023 18.9 tok/s
  10. 10 Baichuan 1-13B 13.3B · Q3_K_M · Jul 2023 18.8 tok/s

The fastest AI models on a GeForce GTX 1070

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 92.3 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 92.3 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 92.3 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 92.3 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 92.3 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 92.3 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 85.4 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 83.9 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 83.9 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 83.9 tok/s

Step by step

How to work out the tokens per second of a GeForce GTX 1070

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

    Find the model in the table

    All 337 models the GeForce GTX 1070 handles are already listed. 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. With 8 GB to work in, that is frequently the difference between a model fitting and not.

  3. 03

    Pin the comparison to one quality level

    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.

  4. 04

    Look at the range, not just the number

    The figures are calculated, not measured. 92.3 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.

  5. 05

    Check the headroom before you decide

    The fit column separates models that just fit from those with room to spare — worth checking against the card's 8 GB before settling on one.

  6. 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 GeForce GTX 1070 compares.

Answers

GeForce GTX 1070 — common questions

01

What is the memory bandwidth of a GeForce GTX 1070?

The GeForce GTX 1070 has 256 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.

02

What type of memory does a GeForce GTX 1070 use?

It uses GDDR5 clocked at 2 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.

03

Who makes the GeForce GTX 1070?

The GeForce GTX 1070 is a NVIDIA product, with the chip manufactured by TSMC, on a 16 nm process.

04

When was the GeForce GTX 1070 released?

The GeForce GTX 1070 was released in June 2016.

05

How much power does a GeForce GTX 1070 use?

The GeForce GTX 1070 has a rated board power of 150 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.

06

How much cache does a GeForce GTX 1070 have?

The GeForce GTX 1070 has 48 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.

07

What are the TFLOPS of a GeForce GTX 1070?

The GeForce GTX 1070 is rated at 101 GFLOPS at half precision and 6.5 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.

08

Does the GeForce GTX 1070 support CUDA?

Yes. The GeForce GTX 1070 reports CUDA compute capability 6.1, which predates tensor cores. 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.

09

What bus interface does the GeForce GTX 1070 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.

10

Is the GeForce GTX 1070 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.

11

Can a GeForce GTX 1070 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 8 GB figures on this page assume it.

12

Would two GeForce GTX 1070 cards be twice as fast?

No. A second GeForce GTX 1070 doubles the memory to 16 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.

13

What AI models can a GeForce GTX 1070 run?

337 of the 679 open-weight language models we track fit on a GeForce GTX 1070 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.

14

What is the largest AI model a GeForce GTX 1070 can run?

The largest model in our catalogue that fits on a GeForce GTX 1070 is Baichuan 1-13B at 13.3B parameters, compressed to Q3_K_M. It generates roughly 18.8 tokens per second and needs about 7.2 GB of the card's memory.

15

How many tokens per second does a GeForce GTX 1070 produce?

It depends on the model. On a GeForce GTX 1070 the fastest model we track is Gemma 3 QAT 1B at about 92.3 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.

16

Can a GeForce GTX 1070 run a 7B model?

Yes. For example a GeForce GTX 1070 runs MetaMath 7B (LLaMa finetune) at Q4_K_M, using about 6.5 GB of memory and generating around 30.4 tokens per second.

17

Can a GeForce GTX 1070 run a 13B model?

Yes. For example a GeForce GTX 1070 runs Gemma 4 12B at Q3_K_M, using about 6.5 GB of memory and generating around 20.8 tokens per second.

18

How much memory does a GeForce GTX 1070 have?

A GeForce GTX 1070 has 8 GB of GDDR5 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.

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