Nanbeige-16B TPS calculator

Open weights Nanbeige LLM Lab 16B parameters November 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

306 of 818 cards that can run it

Smallest card that fits

P102-101

10 GB · Q3_K_M · 19.5 tok/s

Fastest card

B200

212 tok/s · 180 GB

Which GPUs can run Nanbeige-16B?

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

306 cards match

Calculating

					Needs	Quantisation	Fit
212 tok/s 127–339 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	17.8 GB	Q8_0	Comfortable
212 tok/s 127–339 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	17.8 GB	Q8_0	Comfortable
169 tok/s 101–271 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	17.8 GB	Q8_0	Comfortable
169 tok/s 101–271 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	17.8 GB	Q8_0	Comfortable
135 tok/s 81–216 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	17.8 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	17.8 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	17.8 GB	Q8_0	Comfortable
124 tok/s 74–198 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	17.8 GB	Q8_0	Comfortable
111 tok/s 67–178 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.5 GB	Q3_K_M	Tight
110 tok/s 66–176 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	17.8 GB	Q8_0	Comfortable
110 tok/s 66–176 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	17.8 GB	Q8_0	Comfortable
110 tok/s 66–176 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	17.8 GB	Q8_0	Comfortable
104 tok/s 63–167 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	17.8 GB	Q8_0	Comfortable
88.9 tok/s 53–142 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	17.8 GB	Q8_0	Comfortable
88.9 tok/s 53–142 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	17.8 GB	Q8_0	Comfortable
88.9 tok/s 53–142 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	17.8 GB	Q8_0	Comfortable
88.9 tok/s 53–142 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	17.8 GB	Q8_0	Comfortable
88.9 tok/s 53–142 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	17.8 GB	Q8_0	Comfortable
67.7 tok/s 41–108 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	17.8 GB	Q8_0	Comfortable
67.7 tok/s 41–108 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	17.8 GB	Q8_0	Comfortable
56.4 tok/s 34–90 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	17.8 GB	Q8_0	Comfortable
55.8 tok/s 33–89 · low confidence	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	10.4 GB	Q4_K_M	Tight
55.8 tok/s 33–89 · low confidence	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	10.4 GB	Q4_K_M	Tight
55.2 tok/s 33–88 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	17.8 GB	Q8_0	Comfortable
54.3 tok/s 33–87 · low confidence	CMP 90HX NVIDIA	10 GB	760 GB/s	Jul 2021	8.5 GB	Q3_K_M	Tight

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: Nanbeige LLM Lab
Organisation type: Industry
Country: China
Published: 1 November 2023

What it does

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

Domain: Language
Task: Chat, Language modeling/generation, Code generation, Question answering

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: 16B
Training data: 2,500,000,000,000 tokens

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.

Training compute: 2.4 × 10²³ FLOP
How it was established: Operation counting

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)
Training code: Open source

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Likely above 10²³ FLOP: Yes
Record confidence: Likely

Sources

Where this record came from and when it was last checked.

Last updated: 28 November 2025

The extremes

The ten fastest GPUs for Nanbeige-16B

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 Nanbeige-16B

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

P102-101

Memory needed

8.5 GB

Fastest

212 tok/s

Nanbeige-16B is small enough at 16B parameters that hardware is rarely the obstacle — 306 of the cards we track can run it, including cards several years old.

At the low end, a P102-101 handles it — 10 GB, at Q3_K_M, for about 19.5 tokens per second.

Top of the range is the B200, at roughly 212 tokens per second thanks to 8,000 GB/s of bandwidth.

About this model

Nanbeige-16B was published by Nanbeige LLM Lab, in China, in November 2023. industry is the category the publisher falls under.

It works in Language, and is recorded as doing chat, Language modeling/generation, Code generation, Question answering.

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

How fast it runs, and why

Across every card that can run it, the middle of the range is about 19.8 tokens per second, and 259 of them clear the ten tokens per second that roughly matches reading speed.

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.

What went into building it

The training run consumed about 2.4 × 10²³ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 2,500,000,000,000 tokens.

Step by step

How to choose a GPU for Nanbeige-16B

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 Nanbeige-16B — around 8.5 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Nanbeige-16B can slip off a card that handles short questions easily.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage Nanbeige-16B by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

The speed ordering for Nanbeige-16B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 212 tok/s.
05

Check the fit verdict before buying

Tight means Nanbeige-16B 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

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 Nanbeige-16B alone — a card is usually bought for more than one model.

Answers

Nanbeige-16B — common questions

When was Nanbeige-16B released?

Nanbeige-16B was published in November 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 Nanbeige-16B used for?

Nanbeige-16B works in Language, and is recorded as handling chat, Language modeling/generation, Code generation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Nanbeige-16B?

The weights for Nanbeige-16B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

How much compute was used to train Nanbeige-16B?

Around 2.4 × 10²³ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

Can I run Nanbeige-16B if it does not fit in my GPU?

It can be split between the card and system memory, but Nanbeige-16B generates painfully slowly that way — the nearest miss we calculate is short by 3.2 GB. Nothing on this page assumes offloading.

Would two GPUs run Nanbeige-16B faster?

Two cards buy memory rather than speed. That matters for Nanbeige-16B only if one card cannot hold it — 306 can, so a second adds little.

Why does the quantisation differ between cards for Nanbeige-16B?

Because capacity varies, so does how hard Nanbeige-16B has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Nanbeige-16B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 127–339 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.

What GPU do I need to run Nanbeige-16B?

The smallest card in our catalogue that holds Nanbeige-16B is the P102-101, with 10 GB of memory. It runs the model at Q3_K_M using about 8.5 GB, and produces roughly 19.5 tokens per second. 306 cards in total can run it.

How fast is Nanbeige-16B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 212 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 259 of the cards that can run Nanbeige-16B clear that.

How much VRAM does Nanbeige-16B need?

About 8.5 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 Nanbeige-16B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q4_K_M, using about 10.4 GB and generating roughly 55.8 tokens per second — a tight fit.

Can I run Nanbeige-16B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 14.1 GB and generating roughly 43.5 tokens per second — a tight fit.

Can I run Nanbeige-16B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 17.8 GB and generating roughly 35.5 tokens per second — a comfortable fit.

Is Nanbeige-16B open source?

Its weights are published, so Nanbeige-16B 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 Nanbeige-16B have?

Nanbeige-16B has 16B parameters. 16 billion. 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 Nanbeige-16B?

Nanbeige-16B was published by Nanbeige LLM Lab, based in China, categorised as industry.

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