BELLE-Llama2-13B-chat-0.4M TPS calculator

Open weights KE Holdings Inc. (“Beike”) 13B parameters July 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

295 cards that can run it

818 cards we hold specifications for

Smallest card that fits

GeForce GTX 1080 Ti

11 GB · Q3_K_M · 36.2 tok/s

Fastest card

B200

261 tok/s · 180 GB

Which GPUs can run BELLE-Llama2-13B-chat-0.4M?

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

295 cards match

Calculating

					Needs	Quantisation	Fit
261 tok/s 222–313	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	16.9 GB	Q8_0	Comfortable
261 tok/s 222–313	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	16.9 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	16.9 GB	Q8_0	Comfortable
208 tok/s 125–333 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	16.9 GB	Q8_0	Comfortable
166 tok/s 100–266 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	16.9 GB	Q8_0	Comfortable
159 tok/s 135–191	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.9 GB	Q8_0	Comfortable
159 tok/s 135–191	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.9 GB	Q8_0	Comfortable
152 tok/s 91–244 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	16.9 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	16.9 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	16.9 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	16.9 GB	Q8_0	Comfortable
128 tok/s 109–154	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
109 tok/s 93–131	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
109 tok/s 93–131	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	16.9 GB	Q8_0	Comfortable
109 tok/s 93–131	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
109 tok/s 93–131	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
109 tok/s 93–131	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	16.9 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	16.9 GB	Q8_0	Comfortable
83.4 tok/s 50–133 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	16.9 GB	Q8_0	Comfortable
73.0 tok/s 62–88	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	10.1 GB	IQ4_XS	Tight
73.0 tok/s 62–88	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	10.1 GB	IQ4_XS	Tight
69.5 tok/s 42–111 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	16.9 GB	Q8_0	Comfortable
68.0 tok/s 41–109 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	16.9 GB	Q8_0	Comfortable
66.5 tok/s 56–80	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	16.9 GB	Q8_0	Comfortable
66.5 tok/s 56–80	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	16.9 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: KE Holdings Inc. (“Beike”)
Organisation type: Industry
Country: China
Published: 27 July 2023

What it does

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

Domain: Language
Task: Language modeling/generation
Base model: Llama 2-13B

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: 13B
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 (non-commercial)

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.

Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run BELLE-Llama2-13B-chat-0.4M

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 BELLE-Llama2-13B-chat-0.4M

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

GeForce GTX 1080 Ti

Memory needed

9.4 GB

Fastest

261 tok/s

BELLE-Llama2-13B-chat-0.4M reaches a parameter count of 13B. 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: 295.

The entry point is GeForce GTX 1080 Ti, with a memory capacity of 11 GB, running it at a compression of Q3_K_M and producing around 36.2 tokens per second.

Top of the range is B200, generating roughly 261 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

BELLE-Llama2-13B-chat-0.4M was published by KE Holdings Inc. (“Beike”), in the country recorded as China, during July 2023. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation.

It builds on Llama 2-13B. That is the usual way a specialised model is produced.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

Reading the throughput figures

Across every card that can run it, the middle of the range sits at 24.2 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 258 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.

Because the architecture is recorded, the memory column is derived rather than estimated.

Step by step

How to choose a GPU for BELLE-Llama2-13B-chat-0.4M

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 BELLE-Llama2-13B-chat-0.4M, needing around 9.4 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
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 BELLE-Llama2-13B-chat-0.4M.
03

Decide how much compression you will accept

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

Sort by speed

Ranking by tokens per second follows memory bandwidth rather than core counts, for BELLE-Llama2-13B-chat-0.4M. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 261 tok/s.
05

Look at the headroom, not just the fit

Tight means it loads and works with no room to raise the context later, in the case of BELLE-Llama2-13B-chat-0.4M. 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

See what else that card runs

Following a card through to its own page shows every other model it can hold, which is the question that follows once you have settled on BELLE-Llama2-13B-chat-0.4M.

Answers

BELLE-Llama2-13B-chat-0.4M — common questions

BELLE-Llama2-13B-chat-0.4M— 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 IQ4_XS, using about 10.1 GB and generating roughly 73.0 tokens per second. The fit is tight.

BELLE-Llama2-13B-chat-0.4M— 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 13.9 GB and generating roughly 53.5 tokens per second. The fit is tight.

BELLE-Llama2-13B-chat-0.4M— 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 16.9 GB and generating roughly 43.7 tokens per second. The fit is comfortable.

BELLE-Llama2-13B-chat-0.4M— 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.

BELLE-Llama2-13B-chat-0.4M— how many parameters does it have?

It has a parameter count of 13B. 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.

BELLE-Llama2-13B-chat-0.4M— who created it?

It was published by KE Holdings Inc. (“Beike”), based in China, an organisation categorised as industry.

BELLE-Llama2-13B-chat-0.4M— when was it released?

It was published in July 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.

BELLE-Llama2-13B-chat-0.4M— what is it used for?

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

BELLE-Llama2-13B-chat-0.4M— 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.

BELLE-Llama2-13B-chat-0.4M— 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 1.9 GB. Every figure here assumes the whole model is resident on the card.

BELLE-Llama2-13B-chat-0.4M— 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: 295. So a second card is rarely the answer here.

BELLE-Llama2-13B-chat-0.4M— 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.

BELLE-Llama2-13B-chat-0.4M— 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: 222–313 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

BELLE-Llama2-13B-chat-0.4M— what GPU do I need to run it?

The smallest card in our catalogue that holds it is GeForce GTX 1080 Ti, with a memory capacity of 11 GB. It runs the model at a compression of Q3_K_M using about 9.4 GB, and produces roughly 36.2 tokens per second. The number of cards able to run it in total: 295.

BELLE-Llama2-13B-chat-0.4M— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 261 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: 258.

BELLE-Llama2-13B-chat-0.4M— how much VRAM does it need?

It needs about 9.4 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.

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