NTele-R1-32B-V1 TPS calculator

Open weights ZTE 32.8B parameters May 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

132 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX A4500

20 GB · Q3_K_M · 22.3 tok/s

Fastest card

B200

103 tok/s · 180 GB

Which GPUs can run NTele-R1-32B-V1?

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
103 tok/s 62–165 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	35.8 GB	Q8_0	Comfortable
103 tok/s 62–165 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	35.8 GB	Q8_0	Comfortable
82.5 tok/s 49–132 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	35.8 GB	Q8_0	Comfortable
82.5 tok/s 49–132 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	35.8 GB	Q8_0	Comfortable
66.0 tok/s 40–106 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	35.8 GB	Q8_0	Comfortable
63.1 tok/s 38–101 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.8 GB	Q8_0	Comfortable
63.1 tok/s 38–101 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.8 GB	Q8_0	Comfortable
60.4 tok/s 36–97 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	35.8 GB	Q8_0	Comfortable
53.6 tok/s 32–86 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	35.8 GB	Q8_0	Comfortable
53.6 tok/s 32–86 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	35.8 GB	Q8_0	Comfortable
53.6 tok/s 32–86 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	35.8 GB	Q8_0	Comfortable
50.9 tok/s 31–81 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	35.8 GB	Q8_0	Comfortable
43.4 tok/s 26–69 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.8 GB	Q8_0	Comfortable
43.4 tok/s 26–69 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	35.8 GB	Q8_0	Comfortable
43.4 tok/s 26–69 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	35.8 GB	Q8_0	Comfortable
43.4 tok/s 26–69 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.8 GB	Q8_0	Comfortable
43.4 tok/s 26–69 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	35.8 GB	Q8_0	Comfortable
40.0 tok/s 24–64 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	20.5 GB	Q4_K_M	Tight
36.4 tok/s 22–58 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	20.5 GB	Q4_K_M	Tight
35.1 tok/s 21–56 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	28.2 GB	Q6_K	Tight
35.1 tok/s 21–56 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	28.2 GB	Q6_K	Tight
33.6 tok/s 20–54 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	28.2 GB	Q6_K	Tight
33.6 tok/s 20–54 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	28.2 GB	Q6_K	Tight
33.0 tok/s 20–53 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	35.8 GB	Q8_0	Comfortable
33.0 tok/s 20–53 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	35.8 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: ZTE
Organisation type: Industry
Country: China
Published: 12 May 2025

What it does

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

Domain: Mathematics, Language
Task: Code generation, Mathematical reasoning, Language modeling/generation, Question answering
Base model: DeepSeek-R1-Distill-Qwen-32B

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: 32.8B
Training data: tokens
Epochs: 10

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 H800 SXM5
Chips used: 8
Power draw: 11.0 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 (unrestricted)
Training code: Unreleased
Hugging Face: ZTE-AIM

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: Achieving Superior Performance over Qwen3-32B and QwQ-32B Using Only 800 Strategically Curated Samples
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run NTele-R1-32B-V1

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 NTele-R1-32B-V1

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

16.7 GB

Fastest

103 tok/s

With 32.8B parameters, NTele-R1-32B-V1 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 22.3 tokens per second.

A B200 is the fastest we calculate for it: about 103 tokens per second, from 8,000 GB/s of memory bandwidth.

What this model is

NTele-R1-32B-V1 was published by ZTE, in China, in May 2025. It comes out of industry.

It works in Mathematics, Language, and is recorded as doing code generation, Mathematical reasoning, Language modeling/generation, Question answering.

It is derived from DeepSeek-R1-Distill-Qwen-32B rather than trained from scratch, which is the usual way a specialised model is produced.

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 ZTE-AIM organisation on Hugging Face.

What decides the speed

Across every card that can run it, the middle of the range is about 20.1 tokens per second, and 101 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.

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.

Step by step

How to choose a GPU for NTele-R1-32B-V1

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 NTele-R1-32B-V1 — around 16.7 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
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 NTele-R1-32B-V1.
03

Set a quality floor

Compression is what makes NTele-R1-32B-V1 fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

The speed ordering for NTele-R1-32B-V1 is effectively an ordering by memory bandwidth, which is why the B200 tops it at 103 tok/s.
05

Check the fit verdict before buying

Tight means NTele-R1-32B-V1 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

Check the card from the other side

Following a card through to its own page shows every other model it can hold, which is the question that follows once NTele-R1-32B-V1 is settled.

Answers

NTele-R1-32B-V1 — common questions

Who created NTele-R1-32B-V1?

NTele-R1-32B-V1 was published by ZTE, based in China, categorised as industry.

When was NTele-R1-32B-V1 released?

NTele-R1-32B-V1 was published in May 2025.

What is NTele-R1-32B-V1 used for?

NTele-R1-32B-V1 works in Mathematics, Language, and is recorded as handling code generation, Mathematical reasoning, 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 NTele-R1-32B-V1?

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

Can I run NTele-R1-32B-V1 if it does not fit in my GPU?

It can be split between the card and system memory, but NTele-R1-32B-V1 generates painfully slowly that way — the nearest miss we calculate is short by 6.1 GB. Nothing on this page assumes offloading.

Would two GPUs run NTele-R1-32B-V1 faster?

A second card roughly doubles the memory available but not the generation rate. With 132 cards already able to run NTele-R1-32B-V1 alone, the case for pairing is weak.

Why does the quantisation differ between cards for NTele-R1-32B-V1?

Each card is shown running the least-compressed copy it can hold, and NTele-R1-32B-V1 appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these NTele-R1-32B-V1 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 62–165 tok/s on the B200 rather than a single number.

What GPU do I need to run NTele-R1-32B-V1?

The smallest card in our catalogue that holds NTele-R1-32B-V1 is the RTX A4500, with 20 GB of memory. It runs the model at Q3_K_M using about 16.7 GB, and produces roughly 22.3 tokens per second. 132 cards in total can run it.

How fast is NTele-R1-32B-V1 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 103 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 101 of the cards that can run NTele-R1-32B-V1 clear that.

How much VRAM does NTele-R1-32B-V1 need?

About 16.7 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 NTele-R1-32B-V1 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 20.5 GB and generating roughly 40.0 tokens per second — a tight fit.

Is NTele-R1-32B-V1 open source?

Its weights are published, so NTele-R1-32B-V1 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 NTele-R1-32B-V1 have?

NTele-R1-32B-V1 has 32.8B 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.

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