Nemotron-Cascade 14B TPS calculator

Open weights NVIDIA 14.8B parameters December 2025

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 · 19.1 tok/s

Fastest card

B200

229 tok/s · 180 GB

Which GPUs can run Nemotron-Cascade 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
229 tok/s 137–366 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	16.5 GB	Q8_0	Comfortable
229 tok/s 137–366 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	16.5 GB	Q8_0	Comfortable
183 tok/s 110–293 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	16.5 GB	Q8_0	Comfortable
183 tok/s 110–293 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	16.5 GB	Q8_0	Comfortable
146 tok/s 88–234 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	16.5 GB	Q8_0	Comfortable
140 tok/s 84–224 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.5 GB	Q8_0	Comfortable
140 tok/s 84–224 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.5 GB	Q8_0	Comfortable
134 tok/s 80–214 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	16.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	16.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	16.5 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	16.5 GB	Q8_0	Comfortable
113 tok/s 68–180 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	16.5 GB	Q8_0	Comfortable
110 tok/s 66–175 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.8 GB	IQ4_XS	Tight
96.2 tok/s 58–154 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.5 GB	Q8_0	Comfortable
96.2 tok/s 58–154 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	16.5 GB	Q8_0	Comfortable
96.2 tok/s 58–154 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	16.5 GB	Q8_0	Comfortable
96.2 tok/s 58–154 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.5 GB	Q8_0	Comfortable
96.2 tok/s 58–154 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	16.5 GB	Q8_0	Comfortable
73.2 tok/s 44–117 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	16.5 GB	Q8_0	Comfortable
73.2 tok/s 44–117 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	16.5 GB	Q8_0	Comfortable
61.0 tok/s 37–98 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	16.5 GB	Q8_0	Comfortable
60.3 tok/s 36–96 · low confidence	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	9.7 GB	Q4_K_M	Tight
60.3 tok/s 36–96 · low confidence	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	9.7 GB	Q4_K_M	Tight
59.7 tok/s 36–96 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	16.5 GB	Q8_0	Comfortable
58.4 tok/s 35–93 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	16.5 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: NVIDIA
Organisation type: Industry
Country: United States of America
Published: 15 December 2025
Authors: Boxin Wang, Chankyu Lee, Nayeon Lee, Sheng-Chieh Lin, Wenliang Dai, Yang Chen, Yangyi Chen, Zhuolin Yang, Zihan Liu, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping

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
Approach: Supervised fine-tuning (SFT),Reinforcement learning
Base model: Qwen3-14B

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: 14.8B
Training data: tokens
Epochs: 1

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)
Hugging Face: nvidia

How it is classified

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

Record confidence: Likely

Sources

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

Reference: Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Last updated: 30 July 2026

The extremes

The ten fastest GPUs that run Nemotron-Cascade 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 Nemotron-Cascade 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

8.8 GB

Fastest

229 tok/s

Nemotron-Cascade 14B reaches a parameter count of 14.8B. 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: 306.

At the low end it is handled by P102-101, with a memory capacity of 10 GB, running it at a compression of IQ4_XS and producing around 19.1 tokens per second.

At the other end sits B200, generating roughly 229 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

Nemotron-Cascade 14B was published by NVIDIA, in the country recorded as United States of America, during December 2025. 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, Question answering.

Its starting point was an existing base model, Qwen3-14B. That is why it shares the base model's general shape and size.

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. On Hugging Face it is published under the organisation nvidia.

Reading the throughput figures

Half the cards that hold it manage more than 21.4 tokens per second. Exceeding reading speed outright: 266 of them.

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 Nemotron-Cascade 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

Every card here has been checked against Nemotron-Cascade 14B, needing around 8.8 GB at a compression of IQ4_XS. That figure, not the headline performance of a card, is what decides whether it runs.
02

Decide how long your conversations run

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting Nemotron-Cascade 14B.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of IQ4_XS 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

Rank by throughput rather than spec sheet

The speed ordering is effectively an ordering by memory bandwidth, for Nemotron-Cascade 14B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 229 tok/s.
05

Check the fit verdict before buying

Tight means it loads and works with no room to raise the context later, in the case of Nemotron-Cascade 14B. 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

Open the card you have settled on

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond Nemotron-Cascade 14B.

Answers

Nemotron-Cascade 14B — common questions

Nemotron-Cascade 14B— 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 16.5 GB and generating roughly 38.4 tokens per second. The fit is comfortable.

Nemotron-Cascade 14B— 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.

Nemotron-Cascade 14B— how many parameters does it have?

It has a parameter count of 14.8B. "using the pretrained [...] Qwen3-14B-Base". 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.

Nemotron-Cascade 14B— who created it?

It was published by NVIDIA, based in United States of America, an organisation categorised as industry.

Nemotron-Cascade 14B— when was it released?

It was published in December 2025.

Nemotron-Cascade 14B— what is it used for?

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

Nemotron-Cascade 14B— where can I download it?

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

Nemotron-Cascade 14B— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 2.5 GB. Every figure here assumes the whole model is resident on the card.

Nemotron-Cascade 14B— 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: 306. So a second card is rarely the answer here.

Nemotron-Cascade 14B— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Nemotron-Cascade 14B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 137–366 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Nemotron-Cascade 14B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is P102-101, with a memory capacity of 10 GB. It runs the model at a compression of IQ4_XS using about 8.8 GB, and produces roughly 19.1 tokens per second. The number of cards able to run it in total: 306.

Nemotron-Cascade 14B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 229 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: 266.

Nemotron-Cascade 14B— how much VRAM does it need?

It needs about 8.8 GB at a compression of IQ4_XS, 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.

Nemotron-Cascade 14B— 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 Q4_K_M, using about 9.7 GB and generating roughly 60.3 tokens per second. The fit is tight.

Nemotron-Cascade 14B— 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 Q6_K, using about 13.1 GB and generating roughly 47.0 tokens per second. The fit is tight.

Source

Original publication

Record last updated 30 July 2026

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