StableLM - Zephyr 3B TPS calculator

Open weights Stability AI 3B parameters December 2023

Each card below is assessed against this model at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from the card's memory bandwidth and the size of the model once compressed.

Calculated for this model

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q6_K · 17.9 tok/s

Fastest card

B200

1,129 tok/s · 180 GB

Which GPUs can run StableLM - Zephyr 3B?

Set the inputs, read the answer

Context length tokens

A longer conversation needs more memory, which can push this model off smaller cards.

Minimum quality

Hides cards that would only fit the model by compressing it below this point.

Search cards

Card memory

Also show cards that cannot run it

818 cards match

Calculating

					Needs	Quantisation	Fit
1,129 tok/s 678–1,807 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.9 GB	Q8_0	Comfortable
1,129 tok/s 678–1,807 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.9 GB	Q8_0	Comfortable
902 tok/s 541–1,443 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.9 GB	Q8_0	Comfortable
902 tok/s 541–1,443 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.9 GB	Q8_0	Comfortable
721 tok/s 433–1,154 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
690 tok/s 414–1,105 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.9 GB	Q8_0	Comfortable
690 tok/s 414–1,105 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.9 GB	Q8_0	Comfortable
661 tok/s 396–1,057 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.9 GB	Q8_0	Comfortable
586 tok/s 352–938 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
586 tok/s 352–938 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
586 tok/s 352–938 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
556 tok/s 334–890 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
361 tok/s 217–578 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.9 GB	Q8_0	Comfortable
361 tok/s 217–578 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.9 GB	Q8_0	Comfortable
301 tok/s 181–482 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
295 tok/s 177–471 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.9 GB	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

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation: Stability AI
Organisation type: Industry
Country: United Kingdom of Great Britain and Northern Ireland
Published: 7 December 2023

What it does

The problem areas the model was built for. A model can carry several of each.

Domain: Language
Task: Language modeling/generation, Question answering
Base model: StableLM-3B-4E1T

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters: 3B
Training data: tokens

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware: NVIDIA A100 SXM4 80 GB
Chips used: 8
Power draw: 6.3 kW

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights: Open — downloadable
Model access: Open weights (restricted use)
Hugging Face: stabilityai

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence: Confident

Sources

Where this record came from and when it was last checked.

Reference: Introducing Stable LM Zephyr 3B: A New Addition to Stable LM, Bringing Powerful LLM Assistants to Edge Devices
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run StableLM - Zephyr 3B

Ranked by estimated tokens per second, newest card first where speeds tie. Because generation is bound by memory bandwidth, this ordering follows bandwidth rather than any gaming benchmark.

The smallest GPUs that still run StableLM - Zephyr 3B

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

What the numbers mean

What you need to run it

Minimum card

Tesla C1080

Memory needed

3.2 GB

Fastest

1,129 tok/s

StableLM - Zephyr 3B is small enough at 3B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q6_K compression, giving roughly 17.9 tokens per second.

A B200 is the fastest we calculate for it: about 1,129 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

StableLM - Zephyr 3B was published by Stability AI, in United Kingdom of Great Britain and Northern Ireland, in December 2023. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Question answering.

It is derived from StableLM-3B-4E1T rather than trained from scratch, which is the usual way a specialised model is produced.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the stabilityai organisation on Hugging Face.

Understanding the speeds

Across every card that can run it, the middle of the range is about 35.8 tokens per second, and 780 of them clear the ten tokens per second that roughly matches reading speed.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Step by step

How to choose a GPU for StableLM - Zephyr 3B

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Check what it needs before anything else

The table lists every card that can hold StableLM - Zephyr 3B — around 3.2 GB at Q6_K. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason StableLM - Zephyr 3B stops fitting a card that seemed fine.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q6_K on the smallest card that fits. Setting a floor drops the cards that only manage StableLM - Zephyr 3B by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for StableLM - Zephyr 3B follows memory bandwidth, not core counts, which is why the B200 tops it at 1,129 tok/s.
05

Read the fit column last

The fit column separates cards that just manage StableLM - Zephyr 3B from those with room to spare. Buy for the second if the context might grow.
06

See what else that card runs

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for StableLM - Zephyr 3B alone — a card is usually bought for more than one model.

Answers

StableLM - Zephyr 3B — common questions

How accurate are these StableLM - Zephyr 3B speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 678–1,807 tok/s on the B200 rather than a single number.

What GPU do I need to run StableLM - Zephyr 3B?

The smallest card in our catalogue that holds StableLM - Zephyr 3B is the Tesla C1080, with 4 GB of memory. It runs the model at Q6_K using about 3.2 GB, and produces roughly 17.9 tokens per second. 818 cards in total can run it.

How fast is StableLM - Zephyr 3B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,129 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 780 of the cards that can run StableLM - Zephyr 3B clear that.

How much VRAM does StableLM - Zephyr 3B need?

About 3.2 GB at Q6_K compression, which is what the smallest card that runs it uses. Less compression needs more: the figures in the memory column above are recalculated for each card, because each one holds the least-compressed version it can.

Can I run StableLM - Zephyr 3B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 3.9 GB and generating roughly 210 tokens per second — a comfortable fit.

Can I run StableLM - Zephyr 3B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 3.9 GB and generating roughly 129 tokens per second — a comfortable fit.

Can I run StableLM - Zephyr 3B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 3.9 GB and generating roughly 160 tokens per second — a comfortable fit.

Can I run StableLM - Zephyr 3B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 3.9 GB and generating roughly 189 tokens per second — a comfortable fit.

Is StableLM - Zephyr 3B open source?

Its weights are published, so StableLM - Zephyr 3B can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

How many parameters does StableLM - Zephyr 3B have?

StableLM - Zephyr 3B has 3B parameters. 3B. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

Who created StableLM - Zephyr 3B?

StableLM - Zephyr 3B was published by Stability AI, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.

When was StableLM - Zephyr 3B released?

StableLM - Zephyr 3B was published in December 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

What is StableLM - Zephyr 3B used for?

StableLM - Zephyr 3B works in Language, and is recorded as handling language modeling/generation, Question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Where can I download StableLM - Zephyr 3B?

Its weights are published under the stabilityai organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

Can I run StableLM - Zephyr 3B if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down. Our figures for StableLM - Zephyr 3B assume it is fully resident.

Would two GPUs run StableLM - Zephyr 3B faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold StableLM - Zephyr 3B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for StableLM - Zephyr 3B?

Each card is shown running the least-compressed copy it can hold, and StableLM - Zephyr 3B appears at 2 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.

All AI models