SeaLLM-7B-v2.5 TPS calculator

Open weights Alibaba DAMO Academy 8.5B parameters December 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

582 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Quadro 6000

6 GB · IQ4_XS · 14.8 tok/s

Fastest card

B200

397 tok/s · 180 GB

Which GPUs can run SeaLLM-7B-v2.5?

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

582 cards match

Calculating

					Needs	Quantisation	Fit
397 tok/s 238–635 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	9.8 GB	Q8_0	Comfortable
397 tok/s 238–635 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	9.8 GB	Q8_0	Comfortable
317 tok/s 190–507 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	9.8 GB	Q8_0	Comfortable
317 tok/s 190–507 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	9.8 GB	Q8_0	Comfortable
253 tok/s 152–405 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	9.8 GB	Q8_0	Comfortable
243 tok/s 146–388 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	9.8 GB	Q8_0	Comfortable
243 tok/s 146–388 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	9.8 GB	Q8_0	Comfortable
232 tok/s 139–371 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	9.8 GB	Q8_0	Comfortable
206 tok/s 124–330 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	9.8 GB	Q8_0	Comfortable
206 tok/s 124–330 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	9.8 GB	Q8_0	Comfortable
206 tok/s 124–330 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	9.8 GB	Q8_0	Comfortable
195 tok/s 117–313 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	9.8 GB	Q8_0	Comfortable
167 tok/s 100–267 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	9.8 GB	Q8_0	Comfortable
167 tok/s 100–267 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	9.8 GB	Q8_0	Comfortable
167 tok/s 100–267 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	9.8 GB	Q8_0	Comfortable
167 tok/s 100–267 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	9.8 GB	Q8_0	Comfortable
167 tok/s 100–267 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	9.8 GB	Q8_0	Comfortable
132 tok/s 79–211 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.9 GB	Q5_K_M	Tight
127 tok/s 76–203 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	9.8 GB	Q8_0	Comfortable
127 tok/s 76–203 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	9.8 GB	Q8_0	Comfortable
112 tok/s 67–180 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	7.9 GB	Q6_K	Tight
106 tok/s 63–169 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	9.8 GB	Q8_0	Comfortable
103 tok/s 62–166 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	9.8 GB	Q8_0	Comfortable
101 tok/s 61–162 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	9.8 GB	Q8_0	Comfortable
101 tok/s 61–162 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	9.8 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: Alibaba DAMO Academy
Organisation type: Industry
Country: China
Published: 1 December 2023
Authors: Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Zhiqiang Hu, Chenhui Shen, Yew Ken Chia, Xingxuan Li, Jianyu Wang, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing

What it does

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

Domain: Language
Task: Chat
Base model: Gemma 7B

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: 8.5B
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)

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: SeaLLMs -- Large Language Models for Southeast Asia
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run SeaLLM-7B-v2.5

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 SeaLLM-7B-v2.5

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

Quadro 6000

Memory needed

5.4 GB

Fastest

397 tok/s

SeaLLM-7B-v2.5 reaches a parameter count of 8.5B. 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: 582.

At the low end it is handled by Quadro 6000, with a memory capacity of 6 GB, running it at a compression of IQ4_XS and producing around 14.8 tokens per second.

Top of the range is B200, generating roughly 397 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

SeaLLM-7B-v2.5 was published by Alibaba DAMO Academy, in the country recorded as China, during December 2023. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of chat.

It builds on Gemma 7B. That 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.

Reading the throughput figures

Across every card that can run it, the middle of the range sits at 22.3 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 545 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.

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 SeaLLM-7B-v2.5

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

Every card here has been checked against SeaLLM-7B-v2.5, needing around 5.4 GB at a compression of IQ4_XS. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for SeaLLM-7B-v2.5.
03

Choose how far you will compress it

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

Sort by speed

Sort by speed to see how cards rank for SeaLLM-7B-v2.5. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 397 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage it from those with room to spare, in the case of SeaLLM-7B-v2.5. 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

Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for SeaLLM-7B-v2.5.

Answers

SeaLLM-7B-v2.5 — common questions

SeaLLM-7B-v2.5— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 582. So a second card is rarely the answer here.

SeaLLM-7B-v2.5— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

SeaLLM-7B-v2.5— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 238–635 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

SeaLLM-7B-v2.5— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Quadro 6000, with a memory capacity of 6 GB. It runs the model at a compression of IQ4_XS using about 5.4 GB, and produces roughly 14.8 tokens per second. The number of cards able to run it in total: 582.

SeaLLM-7B-v2.5— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 397 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: 545.

SeaLLM-7B-v2.5— how much VRAM does it need?

It needs about 5.4 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.

SeaLLM-7B-v2.5— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q5_K_M, using about 6.9 GB and generating roughly 132 tokens per second. The fit is tight.

SeaLLM-7B-v2.5— 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 Q8_0, using about 9.8 GB and generating roughly 45.3 tokens per second. The fit is tight.

SeaLLM-7B-v2.5— 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 Q8_0, using about 9.8 GB and generating roughly 56.0 tokens per second. The fit is comfortable.

SeaLLM-7B-v2.5— 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 9.8 GB and generating roughly 66.5 tokens per second. The fit is comfortable.

SeaLLM-7B-v2.5— 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.

SeaLLM-7B-v2.5— how many parameters does it have?

It has a parameter count of 8.5B. https://huggingface.co/SeaLLMs/SeaLLM-7B-v2.5. 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.

SeaLLM-7B-v2.5— who created it?

It was published by Alibaba DAMO Academy, based in China, an organisation categorised as industry.

SeaLLM-7B-v2.5— when was it released?

It was published in December 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.

SeaLLM-7B-v2.5— what is it used for?

It works in the domain of Language, and is recorded as handling the task of chat. These are the areas it was designed around; they describe intent rather than a hard boundary.

SeaLLM-7B-v2.5— where can I download it?

The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

SeaLLM-7B-v2.5— 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 1.4 GB. Every figure here assumes the whole model is resident on the card.

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