dots.llm1 TPS calculator

Open weights Rednote 142B parameters July 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

37 cards that can run it

818 cards we hold specifications for

Smallest card that fits

A100 SXM4 80 GB

80 GB · Q3_K_M · 16.4 tok/s

Fastest card

H100 NVL 94 GB

28.9 tok/s · 94 GB

Which GPUs can run dots.llm1?

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

37 cards match

Calculating

					Needs	Quantisation	Fit
28.9 tok/s 17–46 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	78.3 GB	IQ4_XS	Tight
27.2 tok/s 16–44 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	103.1 GB	Q5_K_M	Tight
27.0 tok/s 16–43 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	70.1 GB	Q3_K_M	Tight
27.0 tok/s 16–43 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	70.1 GB	Q3_K_M	Tight
24.6 tok/s 15–39 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	78.3 GB	IQ4_XS	Tight
24.6 tok/s 15–39 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	78.3 GB	IQ4_XS	Tight
24.6 tok/s 15–39 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	78.3 GB	IQ4_XS	Tight
23.9 tok/s 14–38 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	152.7 GB	Q8_0	Tight
23.9 tok/s 14–38 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	152.7 GB	Q8_0	Comfortable
22.1 tok/s 13–35 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	103.1 GB	Q5_K_M	Tight
21.2 tok/s 13–34 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	119.7 GB	Q6_K	Tight
21.2 tok/s 13–34 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	119.7 GB	Q6_K	Tight
19.1 tok/s 11–30 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	152.7 GB	Q8_0	Comfortable
19.1 tok/s 11–30 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	152.7 GB	Q8_0	Comfortable
16.4 tok/s 10–26 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	70.1 GB	Q3_K_M	Tight
16.4 tok/s 10–26 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	70.1 GB	Q3_K_M	Tight
16.4 tok/s 10–26 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	70.1 GB	Q3_K_M	Tight
16.4 tok/s 10–26 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	70.1 GB	Q3_K_M	Tight
16.4 tok/s 10–26 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	70.1 GB	Q3_K_M	Tight
16.4 tok/s 10–26 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	70.1 GB	Q3_K_M	Tight
15.6 tok/s 9–25 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	70.1 GB	Q3_K_M	Tight
15.6 tok/s 9–25 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	70.1 GB	Q3_K_M	Tight
14.0 tok/s 8–22 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	152.7 GB	Q8_0	Comfortable
13.6 tok/s 8–22 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	103.1 GB	Q5_K_M	Tight
13.6 tok/s 8–22 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	103.1 GB	Q5_K_M	Tight

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: Rednote
Organisation type: Industry
Country: China
Published: 6 July 2025
Authors: Bi Huo, Bin Tu, Cheng Qin, Da Zheng, Debing Zhang, Dongjie Zhang, En Li, Fu Guo, Jian Yao, Jie Lou, Junfeng Tian, Li Hu, Ran Zhu, Shengdong Chen, Shuo Liu, Su Guang, Te Wo, Weijun Zhang, Xiaoming Shi, Xinxin Peng, Xing Wu, Yawen Liu, Yuqiu Ji, Ze Wen, Zhenhai Liu, Zichao Li, Zilong Liao

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: 142B
Training data: 11,328,000,000,000 tokens
Batch size: 128,000,000

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: 1.2 × 10²⁴ FLOP
How it was established: Hardware,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 H800 SXM5
Chip-hours: 1,456,000

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: rednote-hilab

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: dots.llm1 Technical Report
Last updated: 19 December 2025

The extremes

The ten fastest GPUs that run dots.llm1

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 dots.llm1

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

A100 SXM4 80 GB

Memory needed

70.1 GB

Fastest

28.9 tok/s

dots.llm1 reaches a parameter count of 142B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 37.

The entry point is A100 SXM4 80 GB, with a memory capacity of 80 GB, running it at a compression of Q3_K_M and producing around 16.4 tokens per second.

The fastest we calculate for it is H100 NVL 94 GB, generating roughly 28.9 tokens per second on the strength of a memory bandwidth of 3,940 GB/s.

Background

dots.llm1 was published by Rednote, in the country recorded as China, during July 2025. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of 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. On Hugging Face it is published under the organisation rednote-hilab.

Reading the throughput figures

The median result is around 16.4 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 35 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.

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.

Training and provenance

The training run consumed about 1.2 × 10²⁴ FLOP, on hardware recorded as NVIDIA H800 SXM5. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 11,328,000,000,000 tokens of text.

Step by step

How to choose a GPU for dots.llm1

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

Start from what it actually needs, which is the requirement of dots.llm1, needing around 70.1 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
02

Match the context to your actual use

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 dots.llm1.
03

Set a quality floor

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

Compare tokens per second, not specifications

The speed ordering is effectively an ordering by memory bandwidth, for dots.llm1. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is H100 NVL 94 GB, at 28.9 tok/s.
05

Check the fit verdict before buying

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of dots.llm1. 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

Check the card from the other side

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond dots.llm1.

Answers

dots.llm1 — common questions

dots.llm1— who created it?

It was published by Rednote, based in China, an organisation categorised as industry.

dots.llm1— when was it released?

It was published in July 2025.

dots.llm1— 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.

dots.llm1— where can I download it?

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

dots.llm1— how much compute was used to train it?

Training consumed around 1.2 × 10²⁴ FLOP, on hardware recorded as NVIDIA H800 SXM5. 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.

dots.llm1— 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 21.8 GB. Every figure here assumes the whole model is resident on the card.

dots.llm1— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 37. So a second card is rarely the answer here.

dots.llm1— 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: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

dots.llm1— 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: 17–46 tok/s on H100 NVL 94 GB. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

dots.llm1— what GPU do I need to run it?

The smallest card in our catalogue that holds it is A100 SXM4 80 GB, with a memory capacity of 80 GB. It runs the model at a compression of Q3_K_M using about 70.1 GB, and produces roughly 16.4 tokens per second. The number of cards able to run it in total: 37.

dots.llm1— how fast is it on a GPU?

It depends on the card. The quickest we calculate is H100 NVL 94 GB, at about 28.9 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: 35.

dots.llm1— how much VRAM does it need?

It needs about 70.1 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.

dots.llm1— 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.

dots.llm1— how many parameters does it have?

It has a parameter count of 142B. a large-scale MoE model that activates 14 billion parameters out of a total of 142 billion 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 19 December 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