Stable LM 2 12B TPS calculator

Open weights Stability AI 12.1B parameters April 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

509 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 5110P

8 GB · Q3_K_M · 19.6 tok/s

Fastest card

B200

279 tok/s · 180 GB

Which GPUs can run Stable LM 2 12B?

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

509 cards match

Calculating

					Needs	Quantisation	Fit
279 tok/s 167–446 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	13.7 GB	Q8_0	Comfortable
279 tok/s 167–446 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	13.7 GB	Q8_0	Comfortable
223 tok/s 134–356 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	13.7 GB	Q8_0	Comfortable
223 tok/s 134–356 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	13.7 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	13.7 GB	Q8_0	Comfortable
171 tok/s 102–273 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	13.7 GB	Q8_0	Comfortable
171 tok/s 102–273 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	13.7 GB	Q8_0	Comfortable
163 tok/s 98–261 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	13.7 GB	Q8_0	Comfortable
145 tok/s 87–232 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	13.7 GB	Q8_0	Comfortable
145 tok/s 87–232 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	13.7 GB	Q8_0	Comfortable
145 tok/s 87–232 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	13.7 GB	Q8_0	Comfortable
140 tok/s 84–224 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.6 GB	Q3_K_M	Tight
137 tok/s 82–220 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	13.7 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.0 GB	Q4_K_M	Tight
117 tok/s 70–188 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	13.7 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	13.7 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	13.7 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	13.7 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	13.7 GB	Q8_0	Comfortable
89.2 tok/s 54–143 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	13.7 GB	Q8_0	Comfortable
89.2 tok/s 54–143 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	13.7 GB	Q8_0	Comfortable
74.4 tok/s 45–119 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	13.7 GB	Q8_0	Comfortable
72.8 tok/s 44–116 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	13.7 GB	Q8_0	Comfortable
72.3 tok/s 43–116 · low confidence	RTX A5000-8Q NVIDIA	8 GB	768 GB/s	Apr 2021	6.6 GB	Q3_K_M	Tight
71.2 tok/s 43–114 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	13.7 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: 8 April 2024

What it does

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

Domain: Language
Task: Language modeling/generation, Translation
Approach: Self-supervised learning
Numerical format: BF16

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: 12.1B
Training data: 2,000,000,000,000 tokens
Epochs: 2

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: 2.9 × 10²³ 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 H100 SXM5 80GB

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)
Training code: Open source

How it is classified

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

Likely above 10²³ FLOP: Yes
Record confidence: Confident

Sources

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

Reference: Introducing Stable LM 2 12B
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Stable LM 2 12B

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 Stable LM 2 12B

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

Xeon Phi 5110P

Memory needed

6.6 GB

Fastest

279 tok/s

Stable LM 2 12B reaches a parameter count of 12.1B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 509.

The least hardware that works is Xeon Phi 5110P, with a memory capacity of 8 GB, running it at a compression of Q3_K_M and producing around 19.6 tokens per second.

At the other end sits B200, generating roughly 279 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

Stable LM 2 12B was published by Stability AI, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during April 2024. It comes out of an organisation categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Translation.

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.

How fast it runs, and why

The median result is around 21.0 tokens per second. Producing text faster than most people read it: 455 of them.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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.

Training and provenance

Producing it required arithmetic totalling around 2.9 × 10²³ FLOP, on hardware recorded as NVIDIA H100 SXM5 80GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 2,000,000,000,000 tokens of text.

Step by step

How to choose a GPU for Stable LM 2 12B

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

Start from what it actually needs, which is the requirement of Stable LM 2 12B, needing around 6.6 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Stable LM 2 12B.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of Q3_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for Stable LM 2 12B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 279 tok/s.
05

Look at the headroom, not just the fit

Tight means it loads and works with no room to raise the context later, in the case of Stable LM 2 12B. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
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 you have settled on Stable LM 2 12B.

Answers

Stable LM 2 12B — common questions

Stable LM 2 12B— when was it released?

It was published in April 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.

Stable LM 2 12B— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Stable LM 2 12B— where can I download it?

The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Stable LM 2 12B— how much compute was used to train it?

Training consumed around 2.9 × 10²³ FLOP, on hardware recorded as NVIDIA H100 SXM5 80GB. 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.

Stable LM 2 12B— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 2.6 GB. Every figure here assumes the whole model is resident on the card.

Stable LM 2 12B— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 509. So a second card is rarely the answer here.

Stable LM 2 12B— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Stable LM 2 12B— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 167–446 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Stable LM 2 12B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Xeon Phi 5110P, with a memory capacity of 8 GB. It runs the model at a compression of Q3_K_M using about 6.6 GB, and produces roughly 19.6 tokens per second. The number of cards able to run it in total: 509.

Stable LM 2 12B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 279 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 455.

Stable LM 2 12B— how much VRAM does it need?

It needs about 6.6 GB at a compression of Q3_K_M, 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.

Stable LM 2 12B— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q3_K_M, using about 6.6 GB and generating roughly 140 tokens per second. The fit is tight.

Stable LM 2 12B— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q5_K_M, using about 9.5 GB and generating roughly 56.8 tokens per second. The fit is tight.

Stable LM 2 12B— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q8_0, using about 13.7 GB and generating roughly 39.4 tokens per second. The fit is tight.

Stable LM 2 12B— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q8_0, using about 13.7 GB and generating roughly 46.7 tokens per second. The fit is comfortable.

Stable LM 2 12B— is it open source?

Its weights are published, so it 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.

Stable LM 2 12B— how many parameters does it have?

It has a parameter count of 12.1B. Precise number given in HF model card. 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.

Stable LM 2 12B— who created it?

It was published by Stability AI, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as industry.

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