SeaLLM-7B-v2 TPS calculator

Open weights Alibaba DAMO Academy 7.4B 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

589 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla K20c

5 GB · Q3_K_M · 27.4 tok/s

Fastest card

B200

459 tok/s · 180 GB

Which GPUs can run SeaLLM-7B-v2?

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

589 cards match

Calculating

					Needs	Quantisation	Fit
459 tok/s 275–735 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.6 GB	Q8_0	Comfortable
459 tok/s 275–735 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.6 GB	Q8_0	Comfortable
367 tok/s 220–587 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.6 GB	Q8_0	Comfortable
367 tok/s 220–587 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.6 GB	Q8_0	Comfortable
293 tok/s 176–469 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.6 GB	Q8_0	Comfortable
281 tok/s 168–449 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.6 GB	Q8_0	Comfortable
281 tok/s 168–449 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.6 GB	Q8_0	Comfortable
269 tok/s 161–430 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.6 GB	Q8_0	Comfortable
238 tok/s 143–381 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.6 GB	Q8_0	Comfortable
238 tok/s 143–381 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.6 GB	Q8_0	Comfortable
238 tok/s 143–381 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.6 GB	Q8_0	Comfortable
226 tok/s 136–362 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.6 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.6 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.6 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.6 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.6 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.6 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.6 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.6 GB	Q8_0	Comfortable
124 tok/s 75–199 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.9 GB	Q6_K	Tight
122 tok/s 73–196 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.6 GB	Q8_0	Comfortable
120 tok/s 72–192 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.6 GB	Q8_0	Comfortable
117 tok/s 70–187 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.6 GB	Q8_0	Comfortable
117 tok/s 70–187 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.6 GB	Q8_0	Comfortable
117 tok/s 70–187 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.6 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: Mistral 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: 7.4B
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

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

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

Tesla K20c

Memory needed

4.3 GB

Fastest

459 tok/s

SeaLLM-7B-v2 is small enough at 7.4B parameters that hardware is rarely the obstacle — 589 of the cards we track can run it, including cards several years old.

The entry point is the Tesla K20c: 5 GB of memory, Q3_K_M compression, roughly 27.4 tokens per second.

Top of the range is the B200, at roughly 459 tokens per second thanks to 8,000 GB/s of bandwidth.

What this model is

SeaLLM-7B-v2 was published by Alibaba DAMO Academy, in China, in December 2023. industry is the category the publisher falls under.

It works in Language, and is recorded as doing chat.

Its starting point was Mistral 7B — most models at this scale are adapted from an existing base rather than built from nothing.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

What decides the speed

Half the cards that hold it manage more than 24.8 tokens per second, and 558 exceed reading speed outright.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

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 SeaLLM-7B-v2

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

Look at what SeaLLM-7B-v2 actually needs — around 4.3 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
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 SeaLLM-7B-v2.
03

Set a quality floor

Compression is what makes SeaLLM-7B-v2 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

Compare tokens per second, not specifications

Sort by speed to see how cards rank for SeaLLM-7B-v2. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 459 tok/s.
05

Check the fit verdict before buying

Tight means SeaLLM-7B-v2 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

See what else that card runs

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

Answers

SeaLLM-7B-v2 — common questions

Is SeaLLM-7B-v2 open source?

Its weights are published, so SeaLLM-7B-v2 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 SeaLLM-7B-v2 have?

SeaLLM-7B-v2 has 7.4B parameters. https://huggingface.co/SeaLLMs/SeaLLM-7B-v2. 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 SeaLLM-7B-v2?

SeaLLM-7B-v2 was published by Alibaba DAMO Academy, based in China, categorised as industry.

When was SeaLLM-7B-v2 released?

SeaLLM-7B-v2 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.

What is SeaLLM-7B-v2 used for?

SeaLLM-7B-v2 works in Language, and is recorded as handling chat. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download SeaLLM-7B-v2?

The weights for SeaLLM-7B-v2 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run SeaLLM-7B-v2 if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded SeaLLM-7B-v2 is rarely worth using — the nearest miss we calculate is short by 1.6 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run SeaLLM-7B-v2 faster?

Capacity adds across cards; throughput does not. Since 589 of the cards we track already hold SeaLLM-7B-v2 on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for SeaLLM-7B-v2?

A larger card holds a more accurate copy. Across the cards that run SeaLLM-7B-v2, 4 compression levels are used; the floor control above pins it to one.

How accurate are these SeaLLM-7B-v2 speed estimates?

These are estimates with real error bars. The fastest result here, 275–735 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run SeaLLM-7B-v2?

The smallest card in our catalogue that holds SeaLLM-7B-v2 is the Tesla K20c, with 5 GB of memory. It runs the model at Q3_K_M using about 4.3 GB, and produces roughly 27.4 tokens per second. 589 cards in total can run it.

How fast is SeaLLM-7B-v2 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 459 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 558 of the cards that can run SeaLLM-7B-v2 clear that.

How much VRAM does SeaLLM-7B-v2 need?

About 4.3 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 SeaLLM-7B-v2 on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 6.9 GB and generating roughly 124 tokens per second — a tight fit.

Can I run SeaLLM-7B-v2 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 8.6 GB and generating roughly 52.4 tokens per second — a comfortable fit.

Can I run SeaLLM-7B-v2 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 8.6 GB and generating roughly 64.9 tokens per second — a comfortable fit.

Can I run SeaLLM-7B-v2 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 8.6 GB and generating roughly 76.9 tokens per second — a comfortable fit.

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