StableLM-2-1.6B TPS calculator

Open weights Stability AI 1.6B parameters January 2024

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 · Q8_0 · 22.4 tok/s

Fastest card

B200

2,060 tok/s · 180 GB

Which GPUs can run StableLM-2-1.6B?

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
2,060 tok/s 1,236–3,297 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.5 GB	Q8_0	Comfortable
2,060 tok/s 1,236–3,297 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.5 GB	Q8_0	Comfortable
1,645 tok/s 987–2,633 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.5 GB	Q8_0	Comfortable
1,645 tok/s 987–2,633 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.5 GB	Q8_0	Comfortable
1,316 tok/s 790–2,105 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
1,259 tok/s 756–2,015 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.5 GB	Q8_0	Comfortable
1,259 tok/s 756–2,015 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.5 GB	Q8_0	Comfortable
1,205 tok/s 723–1,929 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.5 GB	Q8_0	Comfortable
1,070 tok/s 642–1,712 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,070 tok/s 642–1,712 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,070 tok/s 642–1,712 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.5 GB	Q8_0	Comfortable
1,015 tok/s 609–1,624 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
865 tok/s 519–1,385 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
865 tok/s 519–1,385 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.5 GB	Q8_0	Comfortable
865 tok/s 519–1,385 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
865 tok/s 519–1,385 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
865 tok/s 519–1,385 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.5 GB	Q8_0	Comfortable
659 tok/s 395–1,054 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.5 GB	Q8_0	Comfortable
659 tok/s 395–1,054 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.5 GB	Q8_0	Comfortable
549 tok/s 329–879 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
537 tok/s 322–860 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.5 GB	Q8_0	Comfortable
525 tok/s 315–841 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.5 GB	Q8_0	Comfortable
525 tok/s 315–841 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.5 GB	Q8_0	Comfortable
525 tok/s 315–841 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.5 GB	Q8_0	Comfortable
525 tok/s 315–841 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.5 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: 18 January 2024
Authors: Stability AI Language Team

What it does

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

Domain: Language
Task: Language modeling/generation
Approach: Self-supervised learning

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: 1.6B
Training data: 2,000,000,000,000 tokens

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute: 1.9 × 10²² FLOP
How it was established: Operation counting

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 40 GB
Chips used: 512
Power draw: 405.7 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 (non-commercial)
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: Stable LM 2 1.6B
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run StableLM-2-1.6B

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-2-1.6B

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

The hardware side

Minimum card

Tesla C1080

Memory needed

2.5 GB

Fastest

2,060 tok/s

StableLM-2-1.6B is small enough at 1.6B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

At the low end, a Tesla C1080 handles it — 4 GB, at Q8_0, for about 22.4 tokens per second.

A B200 is the fastest we calculate for it: about 2,060 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

StableLM-2-1.6B was published by Stability AI, in United Kingdom of Great Britain and Northern Ireland, in January 2024. industry is the category the publisher falls under.

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

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the stabilityai organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 57.9 tokens per second, and 794 exceed reading speed outright.

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.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

How it was trained

Training it took roughly 1.9 × 10²² FLOP of computation, on NVIDIA A100 SXM4 40 GB — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 2,000,000,000,000 tokens.

Step by step

How to choose a GPU for StableLM-2-1.6B

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

01

Start from the memory column

The table lists every card that can hold StableLM-2-1.6B — around 2.5 GB at Q8_0. That figure, not the card's headline performance, is what decides whether it runs.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context StableLM-2-1.6B can slip off a card that handles short questions easily.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage StableLM-2-1.6B by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

The speed ordering for StableLM-2-1.6B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 2,060 tok/s.
05

Read the fit column last

The fit column separates cards that just manage StableLM-2-1.6B from those with room to spare. Buy for the second if the context might grow.
06

See what else that card runs

Following a card through to its own page shows every other model it can hold, which is the question that follows once StableLM-2-1.6B is settled.

Answers

StableLM-2-1.6B — common questions

Can I run StableLM-2-1.6B 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-2-1.6B assume it is fully resident.

Would two GPUs run StableLM-2-1.6B faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run StableLM-2-1.6B alone, the case for pairing is weak.

Why does the quantisation differ between cards for StableLM-2-1.6B?

Each card is shown running the least-compressed copy it can hold, and StableLM-2-1.6B appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these StableLM-2-1.6B speed estimates?

These are estimates with real error bars. The fastest result here, 1,236–3,297 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run StableLM-2-1.6B?

The smallest card in our catalogue that holds StableLM-2-1.6B is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.5 GB, and produces roughly 22.4 tokens per second. 818 cards in total can run it.

How fast is StableLM-2-1.6B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 2,060 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 794 of the cards that can run StableLM-2-1.6B clear that.

How much VRAM does StableLM-2-1.6B need?

About 2.5 GB at Q8_0 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-2-1.6B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.5 GB and generating roughly 384 tokens per second — a comfortable fit.

Can I run StableLM-2-1.6B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.5 GB and generating roughly 235 tokens per second — a comfortable fit.

Can I run StableLM-2-1.6B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.5 GB and generating roughly 291 tokens per second — a comfortable fit.

Can I run StableLM-2-1.6B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.5 GB and generating roughly 345 tokens per second — a comfortable fit.

Is StableLM-2-1.6B open source?

Its weights are published, so StableLM-2-1.6B 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-2-1.6B have?

StableLM-2-1.6B has 1.6B parameters. Table under Model Architecture gives exact parameter count. 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-2-1.6B?

StableLM-2-1.6B was published by Stability AI, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.

When was StableLM-2-1.6B released?

StableLM-2-1.6B was published in January 2024. 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-2-1.6B used for?

StableLM-2-1.6B works in Language, and is recorded as handling language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download StableLM-2-1.6B?

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.

How much compute was used to train StableLM-2-1.6B?

Around 1.9 × 10²² FLOP, on NVIDIA A100 SXM4 40 GB. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

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