Baichuan 1-13B TPS calculator

Open weights Baichuan 13.3B 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

509 of 818 cards that can run it

Smallest card that fits

Xeon Phi 5110P

8 GB · Q3_K_M · 17.9 tok/s

Fastest card

B200

255 tok/s · 180 GB

Which GPUs can run Baichuan 1-13B?

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

509 cards match

Calculating

					Needs	Quantisation	Fit
255 tok/s 153–409 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	14.9 GB	Q8_0	Comfortable
255 tok/s 153–409 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	14.9 GB	Q8_0	Comfortable
204 tok/s 122–326 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	14.9 GB	Q8_0	Comfortable
204 tok/s 122–326 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	14.9 GB	Q8_0	Comfortable
163 tok/s 98–261 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	14.9 GB	Q8_0	Comfortable
156 tok/s 94–250 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.9 GB	Q8_0	Comfortable
156 tok/s 94–250 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	14.9 GB	Q8_0	Comfortable
149 tok/s 90–239 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	14.9 GB	Q8_0	Comfortable
133 tok/s 80–212 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	14.9 GB	Q8_0	Comfortable
133 tok/s 80–212 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	14.9 GB	Q8_0	Comfortable
133 tok/s 80–212 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	14.9 GB	Q8_0	Comfortable
128 tok/s 77–205 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	7.2 GB	Q3_K_M	Tight
126 tok/s 75–201 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	14.9 GB	Q8_0	Comfortable
115 tok/s 69–184 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.7 GB	Q4_K_M	Tight
107 tok/s 64–172 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.9 GB	Q8_0	Comfortable
107 tok/s 64–172 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	14.9 GB	Q8_0	Comfortable
107 tok/s 64–172 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	14.9 GB	Q8_0	Comfortable
107 tok/s 64–172 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	14.9 GB	Q8_0	Comfortable
107 tok/s 64–172 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	14.9 GB	Q8_0	Comfortable
81.7 tok/s 49–131 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	14.9 GB	Q8_0	Comfortable
81.7 tok/s 49–131 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	14.9 GB	Q8_0	Comfortable
68.1 tok/s 41–109 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	14.9 GB	Q8_0	Comfortable
66.6 tok/s 40–107 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	14.9 GB	Q8_0	Comfortable
66.2 tok/s 40–106 · low confidence	RTX A5000-8Q NVIDIA	8 GB	768 GB/s	Apr 2021	7.2 GB	Q3_K_M	Tight
65.1 tok/s 39–104 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	14.9 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: Baichuan
Organisation type: Industry
Country: China
Published: 11 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, 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: 13.3B
Training data: 1,400,000,000,000 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: 9.4 × 10²² 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 (restricted use)
Training code: Open source
Hugging Face: baichuan-inc

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: Confident

Sources

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

Reference: Baichuan-13B
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for Baichuan 1-13B

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 Baichuan 1-13B

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

Xeon Phi 5110P

Memory needed

7.2 GB

Fastest

255 tok/s

Baichuan 1-13B is small enough at 13.3B parameters that hardware is rarely the obstacle — 509 of the cards we track can run it, including cards several years old.

The entry point is the Xeon Phi 5110P: 8 GB of memory, Q3_K_M compression, roughly 17.9 tokens per second.

Top of the range is the B200, at roughly 255 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

Baichuan 1-13B was published by Baichuan, in China, in July 2023. industry is the category the publisher falls under.

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

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. It is published under the baichuan-inc organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 20.8 tokens per second, and 459 exceed reading speed outright.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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.

What went into building it

Producing it required around 9.4 × 10²² FLOP of arithmetic, which is a statement about the training budget rather than about inference.

It was trained on about 1,400,000,000,000 tokens of text.

Step by step

How to choose a GPU for Baichuan 1-13B

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Check what it needs before anything else

Every card here has been checked against Baichuan 1-13B — around 7.2 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
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 Baichuan 1-13B stops fitting a card that seemed fine.
03

Decide how much compression you will accept

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 Baichuan 1-13B by squeezing it further than you would want.
04

Sort by speed

The speed ordering for Baichuan 1-13B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 255 tok/s.
05

Read the fit column last

Tight means Baichuan 1-13B 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

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Baichuan 1-13B.

Answers

Baichuan 1-13B — common questions

How fast is Baichuan 1-13B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 255 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 459 of the cards that can run Baichuan 1-13B clear that.

How much VRAM does Baichuan 1-13B need?

About 7.2 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 Baichuan 1-13B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q3_K_M, using about 7.2 GB and generating roughly 128 tokens per second — a tight fit.

Can I run Baichuan 1-13B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q5_K_M, using about 10.3 GB and generating roughly 52.0 tokens per second — a tight fit.

Can I run Baichuan 1-13B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 11.8 GB and generating roughly 52.4 tokens per second — a comfortable fit.

Can I run Baichuan 1-13B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 14.9 GB and generating roughly 42.8 tokens per second — a comfortable fit.

Is Baichuan 1-13B open source?

Its weights are published, so Baichuan 1-13B 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 Baichuan 1-13B have?

Baichuan 1-13B has 13.3B 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 Baichuan 1-13B?

Baichuan 1-13B was published by Baichuan, based in China, categorised as industry.

When was Baichuan 1-13B released?

Baichuan 1-13B 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.

What is Baichuan 1-13B used for?

Baichuan 1-13B works in Language, and is recorded as handling language modeling/generation, Question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Where can I download Baichuan 1-13B?

Its weights are published under the baichuan-inc organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

How much compute was used to train Baichuan 1-13B?

Around 9.4 × 10²² 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 Baichuan 1-13B 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 3.3 GB. Our figures for Baichuan 1-13B assume it is fully resident.

Would two GPUs run Baichuan 1-13B faster?

Two cards buy memory rather than speed. That matters for Baichuan 1-13B only if one card cannot hold it — 509 can, so a second adds little.

Why does the quantisation differ between cards for Baichuan 1-13B?

A larger card holds a more accurate copy. Across the cards that run Baichuan 1-13B, 5 compression levels are used; the floor control above pins it to one.

How accurate are these Baichuan 1-13B speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 153–409 tok/s on the B200 rather than a single number.

What GPU do I need to run Baichuan 1-13B?

The smallest card in our catalogue that holds Baichuan 1-13B is the Xeon Phi 5110P, with 8 GB of memory. It runs the model at Q3_K_M using about 7.2 GB, and produces roughly 17.9 tokens per second. 509 cards in total can run it.

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