CausalLM 34B β TPS calculator

Open weights CausalLM 34.4B parameters February 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

132 of 818 cards that can run it

Smallest card that fits

RTX A4500

20 GB · Q3_K_M · 21.3 tok/s

Fastest card

B200

98.5 tok/s · 180 GB

Which GPUs can run CausalLM 34B β?

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

132 cards match

Calculating

					Needs	Quantisation	Fit
98.5 tok/s 59–158 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	37.5 GB	Q8_0	Comfortable
98.5 tok/s 59–158 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	37.5 GB	Q8_0	Comfortable
78.7 tok/s 47–126 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	37.5 GB	Q8_0	Comfortable
78.7 tok/s 47–126 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	37.5 GB	Q8_0	Comfortable
62.9 tok/s 38–101 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	37.5 GB	Q8_0	Comfortable
60.2 tok/s 36–96 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	37.5 GB	Q8_0	Comfortable
60.2 tok/s 36–96 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	37.5 GB	Q8_0	Comfortable
57.6 tok/s 35–92 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	37.5 GB	Q8_0	Comfortable
51.1 tok/s 31–82 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	37.5 GB	Q8_0	Comfortable
51.1 tok/s 31–82 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	37.5 GB	Q8_0	Comfortable
51.1 tok/s 31–82 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	37.5 GB	Q8_0	Comfortable
48.5 tok/s 29–78 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	37.5 GB	Q8_0	Comfortable
41.4 tok/s 25–66 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	37.5 GB	Q8_0	Comfortable
41.4 tok/s 25–66 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	37.5 GB	Q8_0	Comfortable
41.4 tok/s 25–66 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	37.5 GB	Q8_0	Comfortable
41.4 tok/s 25–66 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	37.5 GB	Q8_0	Comfortable
41.4 tok/s 25–66 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	37.5 GB	Q8_0	Comfortable
41.1 tok/s 25–66 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	25.5 GB	Q5_K_M	Tight
41.1 tok/s 25–66 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	25.5 GB	Q5_K_M	Tight
39.4 tok/s 24–63 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.5 GB	Q5_K_M	Tight
39.4 tok/s 24–63 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.5 GB	Q5_K_M	Tight
38.1 tok/s 23–61 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	21.5 GB	Q4_K_M	Tight
34.7 tok/s 21–55 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	21.5 GB	Q4_K_M	Tight
31.5 tok/s 19–50 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	37.5 GB	Q8_0	Comfortable
31.5 tok/s 19–50 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	37.5 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: CausalLM
Country: China
Published: 6 February 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, Question answering

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: 34.4B
Training data: tokens

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 (unrestricted)
Training code: Unreleased
Hugging Face: CausalLM

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: CausalLM 34B β
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for CausalLM 34B β

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 CausalLM 34B β

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

Hardware requirements in practice

Minimum card

RTX A4500

Memory needed

17.5 GB

Fastest

98.5 tok/s

With 34.4B parameters, CausalLM 34B β lands in the range a serious desktop card can handle once the weights are compressed. 132 of the cards we track can run it.

The entry point is the RTX A4500: 20 GB of memory, Q3_K_M compression, roughly 21.3 tokens per second.

Top of the range is the B200, at roughly 98.5 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

CausalLM 34B β was published by CausalLM, in China, in February 2024.

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

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the CausalLM organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 20.9 tokens per second, and 103 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.

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 CausalLM 34B β

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

Look at what CausalLM 34B β actually needs — around 17.5 GB at 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

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context CausalLM 34B β can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of CausalLM 34B β — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for CausalLM 34B β. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 98.5 tok/s.
05

Read the fit column last

The fit column separates cards that just manage CausalLM 34B β from those with room to spare. Buy for the second if the context might grow.
06

Open the card you have settled on

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for CausalLM 34B β alone — a card is usually bought for more than one model.

Answers

CausalLM 34B β — common questions

When was CausalLM 34B β released?

CausalLM 34B β was published in February 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 CausalLM 34B β used for?

CausalLM 34B β works in Language, and is recorded as handling language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download CausalLM 34B β?

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

Can I run CausalLM 34B β if it does not fit in my GPU?

It can be split between the card and system memory, but CausalLM 34B β generates painfully slowly that way — the nearest miss we calculate is short by 7.1 GB. Nothing on this page assumes offloading.

Would two GPUs run CausalLM 34B β faster?

Two cards buy memory rather than speed. That matters for CausalLM 34B β only if one card cannot hold it — 132 can, so a second adds little.

Why does the quantisation differ between cards for CausalLM 34B β?

Because capacity varies, so does how hard CausalLM 34B β has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these CausalLM 34B β 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 59–158 tok/s on the B200 rather than a single number.

What GPU do I need to run CausalLM 34B β?

The smallest card in our catalogue that holds CausalLM 34B β is the RTX A4500, with 20 GB of memory. It runs the model at Q3_K_M using about 17.5 GB, and produces roughly 21.3 tokens per second. 132 cards in total can run it.

How fast is CausalLM 34B β on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 98.5 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 103 of the cards that can run CausalLM 34B β clear that.

How much VRAM does CausalLM 34B β need?

About 17.5 GB at Q3_K_M 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 CausalLM 34B β on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 21.5 GB and generating roughly 38.1 tokens per second — a tight fit.

Is CausalLM 34B β open source?

Its weights are published, so CausalLM 34B β 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 CausalLM 34B β have?

CausalLM 34B β has 34.4B parameters. 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 CausalLM 34B β?

CausalLM 34B β was published by CausalLM, based in China.

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