BELLE-LLaMA-EXT-7B TPS calculator

Open weights KE Holdings Inc. (“Beike”) 7B parameters April 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 · 18.1 tok/s

Fastest card

B200

484 tok/s · 180 GB

Which GPUs can run BELLE-LLaMA-EXT-7B?

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
484 tok/s 411–581	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.8 GB	Q8_0	Comfortable
484 tok/s 411–581	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.8 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.8 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.8 GB	Q8_0	Comfortable
309 tok/s 185–495 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.8 GB	Q8_0	Comfortable
296 tok/s 251–355	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.8 GB	Q8_0	Comfortable
296 tok/s 251–355	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.8 GB	Q8_0	Comfortable
283 tok/s 170–453 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.8 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.8 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.8 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.8 GB	Q8_0	Comfortable
238 tok/s 203–286	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.8 GB	Q8_0	Comfortable
203 tok/s 173–244	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.8 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.8 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.8 GB	Q8_0	Comfortable
131 tok/s 111–157	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	7.1 GB	Q6_K	Tight
129 tok/s 77–206 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.8 GB	Q8_0	Comfortable
126 tok/s 76–202 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.8 GB	Q8_0	Comfortable
123 tok/s 105–148	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.8 GB	Q8_0	Comfortable
123 tok/s 105–148	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.8 GB	Q8_0	Comfortable
123 tok/s 105–148	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.8 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: KE Holdings Inc. (“Beike”)
Organisation type: Industry
Country: China
Published: 16 April 2023
Authors: Yunjie Ji, Yan Gong, Yong Deng, Yiping Peng, Qiang Niu, Baochang Ma, Xiangang Li

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-7B
Numerical format: BF16

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: 7B
Training data: 3,400,000,000 tokens
Epochs: 3

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.

How it was established: Operation counting
Fine-tuning compute: 4.3 × 10²⁰ FLOP

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 A100 SXM4 80 GB
Chips used: 8
Power draw: 6.4 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 (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.

Reference: Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run BELLE-LLaMA-EXT-7B

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-LLaMA-EXT-7B

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

5.1 GB

Fastest

484 tok/s

BELLE-LLaMA-EXT-7B is small enough at 7B parameters that hardware is rarely the obstacle — 582 of the cards we track can run it, including cards several years old.

At the low end, a Quadro 6000 handles it — 6 GB, at IQ4_XS, for about 18.1 tokens per second.

Top of the range is the B200, at roughly 484 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

BELLE-LLaMA-EXT-7B was published by KE Holdings Inc. (“Beike”), in China, in April 2023. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation.

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

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all.

Understanding the speeds

The median result is around 26.1 tokens per second; 552 cards produce text faster than most people read it.

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.

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

Training and provenance

The training set ran to roughly 3,400,000,000 tokens.

Step by step

How to choose a GPU for BELLE-LLaMA-EXT-7B

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

The table lists every card that can hold BELLE-LLaMA-EXT-7B — around 5.1 GB at IQ4_XS. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason BELLE-LLaMA-EXT-7B stops fitting a card that seemed fine.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of BELLE-LLaMA-EXT-7B — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

Ranking by tokens per second for BELLE-LLaMA-EXT-7B follows memory bandwidth, not core counts, which is why the B200 tops it at 484 tok/s.
05

Read the fit column last

The fit column separates cards that just manage BELLE-LLaMA-EXT-7B from those with room to spare. Buy for the second if the context might grow.
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. Worth a look before buying for BELLE-LLaMA-EXT-7B alone — a card is usually bought for more than one model.

Answers

BELLE-LLaMA-EXT-7B — common questions

Can I run BELLE-LLaMA-EXT-7B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 7.1 GB and generating roughly 131 tokens per second — a tight fit.

Can I run BELLE-LLaMA-EXT-7B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 8.8 GB and generating roughly 55.2 tokens per second — a comfortable fit.

Can I run BELLE-LLaMA-EXT-7B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 8.8 GB and generating roughly 68.4 tokens per second — a comfortable fit.

Can I run BELLE-LLaMA-EXT-7B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 8.8 GB and generating roughly 81.1 tokens per second — a comfortable fit.

Is BELLE-LLaMA-EXT-7B open source?

Its weights are published, so BELLE-LLaMA-EXT-7B 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 BELLE-LLaMA-EXT-7B have?

BELLE-LLaMA-EXT-7B has 7B 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.

Who created BELLE-LLaMA-EXT-7B?

BELLE-LLaMA-EXT-7B was published by KE Holdings Inc. (“Beike”), based in China, categorised as industry.

When was BELLE-LLaMA-EXT-7B released?

BELLE-LLaMA-EXT-7B was published in April 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 BELLE-LLaMA-EXT-7B used for?

BELLE-LLaMA-EXT-7B works in Language, and is recorded as handling language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download BELLE-LLaMA-EXT-7B?

The weights for BELLE-LLaMA-EXT-7B 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 BELLE-LLaMA-EXT-7B if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down — the nearest miss we calculate is short by 1.0 GB. Our figures for BELLE-LLaMA-EXT-7B assume it is fully resident.

Would two GPUs run BELLE-LLaMA-EXT-7B faster?

Capacity adds across cards; throughput does not. Since 582 of the cards we track already hold BELLE-LLaMA-EXT-7B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for BELLE-LLaMA-EXT-7B?

Each card is shown running the least-compressed copy it can hold, and BELLE-LLaMA-EXT-7B appears at 3 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these BELLE-LLaMA-EXT-7B speed estimates?

These are estimates with real error bars. The fastest result here, 411–581 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 BELLE-LLaMA-EXT-7B?

The smallest card in our catalogue that holds BELLE-LLaMA-EXT-7B is the Quadro 6000, with 6 GB of memory. It runs the model at IQ4_XS using about 5.1 GB, and produces roughly 18.1 tokens per second. 582 cards in total can run it.

How fast is BELLE-LLaMA-EXT-7B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 484 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 552 of the cards that can run BELLE-LLaMA-EXT-7B clear that.

How much VRAM does BELLE-LLaMA-EXT-7B need?

About 5.1 GB at IQ4_XS 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.

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