CausalLM 14B TPS calculator

Open weights CausalLM 14.7B parameters October 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

306 cards that can run it

818 cards we hold specifications for

Smallest card that fits

P102-101

10 GB · IQ4_XS · 19.3 tok/s

Fastest card

B200

230 tok/s · 180 GB

Which GPUs can run CausalLM 14B?

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

306 cards match

Calculating

					Needs	Quantisation	Fit
230 tok/s 138–369 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	16.4 GB	Q8_0	Comfortable
230 tok/s 138–369 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	16.4 GB	Q8_0	Comfortable
184 tok/s 110–294 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	16.4 GB	Q8_0	Comfortable
184 tok/s 110–294 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	16.4 GB	Q8_0	Comfortable
147 tok/s 88–236 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	16.4 GB	Q8_0	Comfortable
141 tok/s 85–225 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.4 GB	Q8_0	Comfortable
141 tok/s 85–225 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.4 GB	Q8_0	Comfortable
135 tok/s 81–216 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	16.4 GB	Q8_0	Comfortable
120 tok/s 72–191 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	16.4 GB	Q8_0	Comfortable
120 tok/s 72–191 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	16.4 GB	Q8_0	Comfortable
120 tok/s 72–191 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	16.4 GB	Q8_0	Comfortable
114 tok/s 68–182 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	16.4 GB	Q8_0	Comfortable
110 tok/s 66–177 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.7 GB	IQ4_XS	Tight
96.8 tok/s 58–155 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.4 GB	Q8_0	Comfortable
96.8 tok/s 58–155 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	16.4 GB	Q8_0	Comfortable
96.8 tok/s 58–155 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	16.4 GB	Q8_0	Comfortable
96.8 tok/s 58–155 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.4 GB	Q8_0	Comfortable
96.8 tok/s 58–155 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	16.4 GB	Q8_0	Comfortable
73.7 tok/s 44–118 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	16.4 GB	Q8_0	Comfortable
73.7 tok/s 44–118 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	16.4 GB	Q8_0	Comfortable
61.4 tok/s 37–98 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	16.4 GB	Q8_0	Comfortable
60.7 tok/s 36–97 · low confidence	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	9.6 GB	Q4_K_M	Tight
60.7 tok/s 36–97 · low confidence	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	9.6 GB	Q4_K_M	Tight
60.1 tok/s 36–96 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	16.4 GB	Q8_0	Comfortable
58.8 tok/s 35–94 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	16.4 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: 22 October 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: Qwen-14B

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: 14.7B
Training data: 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.

How it was established: Operation counting
Fine-tuning compute: 1.1 × 10²⁰ FLOP

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: 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: TL;DR: Perhaps better than all existing models < 70B, in most quantitative evaluations...
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run CausalLM 14B

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 14B

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

P102-101

Memory needed

8.7 GB

Fastest

230 tok/s

CausalLM 14B is small enough at 14.7B parameters that hardware is rarely the obstacle — 306 of the cards we track can run it, including cards several years old.

At the low end, a P102-101 handles it — 10 GB, at IQ4_XS, for about 19.3 tokens per second.

A B200 is the fastest we calculate for it: about 230 tokens per second, from 8,000 GB/s of memory bandwidth.

Background

CausalLM 14B was published by CausalLM, in China, in October 2023.

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

It builds on Qwen-14B, which is why it shares that model's general shape and size.

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 CausalLM organisation on Hugging Face.

Reading the throughput figures

Across every card that can run it, the middle of the range is about 21.5 tokens per second, and 266 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.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

Step by step

How to choose a GPU for CausalLM 14B

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 CausalLM 14B — around 8.7 GB at IQ4_XS. 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 CausalLM 14B stops fitting a card that seemed fine.
03

Set a quality floor

Compression is what makes CausalLM 14B fit smaller cards, at some cost in accuracy — IQ4_XS on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Rank by throughput rather than spec sheet

The speed ordering for CausalLM 14B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 230 tok/s.
05

Check the fit verdict before buying

Tight means CausalLM 14B loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
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 14B alone — a card is usually bought for more than one model.

Answers

CausalLM 14B — common questions

What is CausalLM 14B used for?

CausalLM 14B 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 14B?

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 14B if it does not fit in my GPU?

It can be split between the card and system memory, but CausalLM 14B generates painfully slowly that way — the nearest miss we calculate is short by 2.4 GB. Nothing on this page assumes offloading.

Would two GPUs run CausalLM 14B faster?

Capacity adds across cards; throughput does not. Since 306 of the cards we track already hold CausalLM 14B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for CausalLM 14B?

Each card is shown running the least-compressed copy it can hold, and CausalLM 14B appears at 4 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these CausalLM 14B 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 138–369 tok/s on the B200 rather than a single number.

What GPU do I need to run CausalLM 14B?

The smallest card in our catalogue that holds CausalLM 14B is the P102-101, with 10 GB of memory. It runs the model at IQ4_XS using about 8.7 GB, and produces roughly 19.3 tokens per second. 306 cards in total can run it.

How fast is CausalLM 14B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 230 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 266 of the cards that can run CausalLM 14B clear that.

How much VRAM does CausalLM 14B need?

About 8.7 GB at IQ4_XS 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 14B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q4_K_M, using about 9.6 GB and generating roughly 60.7 tokens per second — a tight fit.

Can I run CausalLM 14B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 13.0 GB and generating roughly 47.3 tokens per second — a tight fit.

Can I run CausalLM 14B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 16.4 GB and generating roughly 38.6 tokens per second — a comfortable fit.

Is CausalLM 14B open source?

Its weights are published, so CausalLM 14B 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 14B have?

CausalLM 14B has 14.7B 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 14B?

CausalLM 14B was published by CausalLM, based in China.

When was CausalLM 14B released?

CausalLM 14B was published in October 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.

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