BELLE-LLaMA-7B-0.6M-enc TPS calculator

Open weights KE Holdings Inc. (“Beike”) 7B parameters June 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-7B-0.6M-enc?

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: 12 June 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-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: 7B
Training data: tokens
Epochs: 3

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-LLaMA-7B-0.6M-enc

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-7B-0.6M-enc

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-7B-0.6M-enc 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.

A B200 is the fastest we calculate for it: about 484 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

BELLE-LLaMA-7B-0.6M-enc was published by KE Holdings Inc. (“Beike”), in China, in June 2023. It comes out of industry.

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.

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.

Understanding the speeds

Half the cards that hold it manage more than 26.1 tokens per second, and 552 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.

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

Step by step

How to choose a GPU for BELLE-LLaMA-7B-0.6M-enc

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

Look at what BELLE-LLaMA-7B-0.6M-enc actually needs — around 5.1 GB at IQ4_XS. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

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-LLaMA-7B-0.6M-enc.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of BELLE-LLaMA-7B-0.6M-enc — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Ranking by tokens per second for BELLE-LLaMA-7B-0.6M-enc follows memory bandwidth, not core counts, which is why the B200 tops it at 484 tok/s.
05

Check the fit verdict before buying

A tight fit runs BELLE-LLaMA-7B-0.6M-enc but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond BELLE-LLaMA-7B-0.6M-enc.

Answers

BELLE-LLaMA-7B-0.6M-enc — common questions

What GPU do I need to run BELLE-LLaMA-7B-0.6M-enc?

The smallest card in our catalogue that holds BELLE-LLaMA-7B-0.6M-enc 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-7B-0.6M-enc 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-7B-0.6M-enc clear that.

How much VRAM does BELLE-LLaMA-7B-0.6M-enc 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.

Can I run BELLE-LLaMA-7B-0.6M-enc 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-7B-0.6M-enc 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-7B-0.6M-enc 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-7B-0.6M-enc 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-7B-0.6M-enc open source?

Its weights are published, so BELLE-LLaMA-7B-0.6M-enc 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-7B-0.6M-enc have?

BELLE-LLaMA-7B-0.6M-enc 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-7B-0.6M-enc?

BELLE-LLaMA-7B-0.6M-enc was published by KE Holdings Inc. (“Beike”), based in China, categorised as industry.

When was BELLE-LLaMA-7B-0.6M-enc released?

BELLE-LLaMA-7B-0.6M-enc was published in June 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-7B-0.6M-enc used for?

BELLE-LLaMA-7B-0.6M-enc 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-7B-0.6M-enc?

The weights for BELLE-LLaMA-7B-0.6M-enc 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-7B-0.6M-enc 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 BELLE-LLaMA-7B-0.6M-enc is rarely worth using — the nearest miss we calculate is short by 1.0 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run BELLE-LLaMA-7B-0.6M-enc faster?

Capacity adds across cards; throughput does not. Since 582 of the cards we track already hold BELLE-LLaMA-7B-0.6M-enc on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for BELLE-LLaMA-7B-0.6M-enc?

Because capacity varies, so does how hard BELLE-LLaMA-7B-0.6M-enc has to be squeezed — 3 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these BELLE-LLaMA-7B-0.6M-enc speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 411–581 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

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