Calculate the TPS of the GeForce GTX 970M on local AI models

NVIDIA 6 GB GDDR5 120 GB/s October 2014

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

266 models it can run

679 models in our catalogue altogether

Largest model it holds

Qwen-VL

9.6B · Q3_K_M · 12.2 tok/s

Fastest model

Gemma 3 QAT 1B

43.3 tok/s · 1B

Which AI models can run on a GeForce GTX 970M?

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.

266 models match

Calculating
Quantisation Fit
43.3 tok/s

15–87 · low confidence

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

15–87 · low confidence

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

15–87 · low confidence

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

15–87 · low confidence

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

15–87 · low confidence

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

15–87 · low confidence

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

14–80 · low confidence

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

14–79 · low confidence

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

14–79 · low confidence

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

14–79 · low confidence

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

14–79 · low confidence

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

13–72 · low confidence

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

13–72 · low confidence

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

13–72 · low confidence

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

13–72 · low confidence

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

12–70 · low confidence

Llama 3.2 1B 1.2B Sep 2024 2.2 GB 113k tokens Q8_0 Comfortable
34.7 tok/s

12–69 · low confidence

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

12–67 · low confidence

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

12–67 · low confidence

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

12–67 · low confidence

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

12–67 · low confidence

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

12–67 · low confidence

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

12–67 · low confidence

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

12–67 · low confidence

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

12–67 · 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 970M 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
6 GB
Memory bandwidth
120 GB/s
Memory type
GDDR5
Memory bus width
192 bit
Memory clock
1.25 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
GM204
Architecture
Maxwell 2.0
Generation
GeForce 900M
Foundry
TSMC
Process size
28 nm
Transistors
5.2 billion
Transistor density
13,100 K/mm²
Die size
398 mm²
Package
BGA-1745
Released
7 October 2014

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
924 MHz
Boost clock
1.04 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
1,280
Texture mapping units
80
Render output units
48
Streaming multiprocessors
10
L1 cache
48 KB
L2 cache
1.5 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.

Single precision (FP32)
2.7 TFLOPS
Double precision (FP64)
83 GFLOPS
Pixel rate
50 GPixel/s
Texture rate
83 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 connectors
None
Bus interface
MXM-B (3.0)
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
5.2
DirectX
12.1
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
Shader model
6.8

Listings

Where to buy a GeForce GTX 970M

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

6 GB

Bandwidth

120 GB/s

Largest model

Qwen-VL

At 6 GB of GDDR5 the GeForce GTX 970M is limited to the smaller end of the catalogue. About 5.4 GB is actually available to a runtime, and a model has to fit entirely inside it before generating anything at all.

At 120 GB/s across a 192-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.

That comes from a 1.25 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.

Put together, the largest model that fits is Qwen-VL at 9.6B, running Q3_K_M and producing around 12.2 tokens per second.

The chip and how it was built

The GeForce GTX 970M is built on the GM204 graphics processor, using NVIDIA's Maxwell 2.0 architecture, as part of the GeForce 900M generation.

The chip is manufactured by TSMC, on a 28 nm process, with a die measuring 398 mm², holding 5.2 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 October 2014, roughly 11 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

FP64

83 GFLOPS

Double-precision throughput is 83 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 924 MHz at base to 1.04 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 970M has 48 KB of L1 cache, backed by 1.5 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 1,280 shading units, 80 texture mapping units, and 48 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

The board occupies a 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 MXM-B (3.0). 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 970M

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 Qwen3.5-9B 9B · Q3_K_M · Feb 2026 13.0 tok/s
  2. 02 NVIDIA-Nemotron-Nano-9B-v2 9B · Q3_K_M · Aug 2025 13.0 tok/s
  3. 03 Ovis2.5 9B 9B · Q3_K_M · Aug 2025 13.0 tok/s
  4. 04 GLM-4.1V-Thinking 9B · Q3_K_M · Aug 2025 13.0 tok/s
  5. 05 MamayLM 9B · Q3_K_M · Apr 2025 13.0 tok/s
  6. 06 GLM-4-9B-0414 9B · Q3_K_M · Apr 2025 13.0 tok/s
  7. 07 SimPO 9B · Q3_K_M · Nov 2024 13.0 tok/s
  8. 08 GLM-4V-9B 9B · Q3_K_M · Jun 2024 13.0 tok/s
  9. 09 Persimmon-8B 9.3B · Q3_K_M · Sep 2023 12.6 tok/s
  10. 10 Qwen-VL 9.6B · Q3_K_M · Aug 2023 12.2 tok/s

The fastest AI models on a GeForce GTX 970M

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 43.3 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 43.3 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 43.3 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 43.3 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 43.3 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 43.3 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 40.1 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 39.4 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 39.4 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 39.4 tok/s

Step by step

How to work out the tokens per second of a GeForce GTX 970M

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

    All 266 models the GeForce GTX 970M handles are already listed. The search box takes a name or a size such as 27b, which matches on parameter count.

  2. 02

    Set the context length you will actually use

    Drag the slider to the conversation length you plan to work at. The cache grows with the conversation, and on 6 GB it is often what pushes a large model over the edge.

  3. 03

    Set a minimum quality if you need one

    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

    Take the range as the answer

    The figures are calculated, not measured. 43.3 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 memory column before committing

    The fit column separates models that just fit from those with room to spare — worth checking against the card's 6 GB before settling on one.

  6. 06

    Cross-check against other hardware

    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 970M compares.

Answers

GeForce GTX 970M — common questions

01

When was the GeForce GTX 970M released?

The GeForce GTX 970M was released in October 2014.

02

How much cache does a GeForce GTX 970M have?

The GeForce GTX 970M has 48 KB of L1 cache, and 1.5 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.

03

Does the GeForce GTX 970M support CUDA?

Yes. The GeForce GTX 970M reports CUDA compute capability 5.2, 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.

04

What bus interface does the GeForce GTX 970M use?

It uses MXM-B (3.0). 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.

05

Is the GeForce GTX 970M 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 266 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.

06

Can a GeForce GTX 970M run a model that does not fit in its memory?

Offloading past the card's 6 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.

07

Would two GeForce GTX 970M cards be twice as fast?

No. A second GeForce GTX 970M doubles the memory to 12 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.

08

What AI models can a GeForce GTX 970M run?

266 of the 679 open-weight language models we track fit on a GeForce GTX 970M 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.

09

What is the largest AI model a GeForce GTX 970M can run?

The largest model in our catalogue that fits on a GeForce GTX 970M is Qwen-VL at 9.6B parameters, compressed to Q3_K_M. It generates roughly 12.2 tokens per second and needs about 5.4 GB of the card's memory.

10

How many tokens per second does a GeForce GTX 970M produce?

It depends on the model. On a GeForce GTX 970M the fastest model we track is Gemma 3 QAT 1B at about 43.3 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.

11

Can a GeForce GTX 970M run a 7B model?

Yes. For example a GeForce GTX 970M runs MetaMath 7B (Mistral finetune) at IQ4_XS, using about 5.1 GB of memory and generating around 15.2 tokens per second.

12

How much memory does a GeForce GTX 970M have?

A GeForce GTX 970M has 6 GB of GDDR5 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 5.4 GB available for a model and its conversation.

13

What is the memory bandwidth of a GeForce GTX 970M?

The GeForce GTX 970M has 120 GB/s of memory bandwidth, across a 192-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.

14

What type of memory does a GeForce GTX 970M use?

It uses GDDR5 clocked at 1.25 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.

15

Who makes the GeForce GTX 970M?

The GeForce GTX 970M is a NVIDIA product, with the chip manufactured by TSMC, on a 28 nm process.

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