Baichuan-Omni-1.5 TPS calculator

Open weights Baichuan 11B parameters January 2025

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 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 5110P

8 GB · IQ4_XS · 19.7 tok/s

Fastest card

B200

308 tok/s · 180 GB

Which GPUs can run Baichuan-Omni-1.5?

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
308 tok/s 185–493 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	12.5 GB	Q8_0	Comfortable
308 tok/s 185–493 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	12.5 GB	Q8_0	Comfortable
246 tok/s 148–394 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	12.5 GB	Q8_0	Comfortable
246 tok/s 148–394 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	12.5 GB	Q8_0	Comfortable
197 tok/s 118–315 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	12.5 GB	Q8_0	Comfortable
188 tok/s 113–301 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	12.5 GB	Q8_0	Comfortable
188 tok/s 113–301 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	12.5 GB	Q8_0	Comfortable
180 tok/s 108–288 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	12.5 GB	Q8_0	Comfortable
160 tok/s 96–256 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	12.5 GB	Q8_0	Comfortable
160 tok/s 96–256 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	12.5 GB	Q8_0	Comfortable
160 tok/s 96–256 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	12.5 GB	Q8_0	Comfortable
152 tok/s 91–243 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	12.5 GB	Q8_0	Comfortable
141 tok/s 85–225 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.7 GB	IQ4_XS	Tight
129 tok/s 78–207 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	12.5 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	12.5 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	12.5 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	12.5 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	12.5 GB	Q8_0	Comfortable
107 tok/s 64–172 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.6 GB	Q5_K_M	Tight
98.5 tok/s 59–158 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	12.5 GB	Q8_0	Comfortable
98.5 tok/s 59–158 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	12.5 GB	Q8_0	Comfortable
82.1 tok/s 49–131 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	12.5 GB	Q8_0	Comfortable
80.3 tok/s 48–129 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	12.5 GB	Q8_0	Comfortable
78.6 tok/s 47–126 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	12.5 GB	Q8_0	Comfortable
78.6 tok/s 47–126 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	12.5 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: 26 January 2025
Authors: Yadong Li, Jun Liu, Tao Zhang, Tao Zhang, Song Chen, Tianpeng Li, Zehuan Li, Lijun Liu, Lingfeng Ming, Guosheng Dong, Da Pan, Chong Li, Yuanbo Fang, Dongdong Kuang, Mingrui Wang, Chenglin Zhu, Youwei Zhang, Hongyu Guo, Fengyu Zhang, Yuran Wang, Bowen Ding, Wei Song, Xu Li, Yuqi Huo, Zheng Liang, Shusen Zhang, Xin Wu, Shuai Zhao, Linchu Xiong, Yozhen Wu, Jiahui Ye, Wenhao Lu, Bowen Li, Yan Zhang, Y…

What it does

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

Domain: Multimodal, Language, Speech, Vision, Video, Audio
Task: Language modeling/generation, Question answering, Audio question answering, Speech recognition (ASR), Speech-to-text, Visual question answering, Image captioning, Speech synthesis, Text-to-speech (TTS), Video, Video classification

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: 11B
Training data: 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: 3.3 × 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: Unreleased
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.

Record confidence: Likely

Sources

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

Reference: Baichuan-Omni-1.5 Technical Report
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Baichuan-Omni-1.5

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-Omni-1.5

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

What you need to run it

Minimum card

Xeon Phi 5110P

Memory needed

6.7 GB

Fastest

308 tok/s

Baichuan-Omni-1.5 is small enough at 11B parameters that hardware is rarely the obstacle — 509 of the cards we track can run it, including cards several years old.

The least hardware that works is a Xeon Phi 5110P. Its 8 GB is enough at IQ4_XS compression, giving roughly 19.7 tokens per second.

Top of the range is the B200, at roughly 308 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

Baichuan-Omni-1.5 was published by Baichuan, in China, in January 2025. industry is the category the publisher falls under.

It works in Multimodal, Language, Speech, Vision, Video, Audio, and is recorded as doing language modeling/generation, Question answering, Audio question answering, Speech recognition (ASR), Speech-to-text, Visual question answering, Image captioning, Speech synthesis, Text-to-speech (TTS), Video, Video classification.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the baichuan-inc organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 21.2 tokens per second, and 460 exceed reading speed outright.

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.

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.

How it was trained

Training it took roughly 3.3 × 10²² FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

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

Step by step

How to choose a GPU for Baichuan-Omni-1.5

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

Look at what Baichuan-Omni-1.5 actually needs — around 6.7 GB at IQ4_XS. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Baichuan-Omni-1.5 can slip off a card that handles short questions easily.
03

Choose how far you will compress it

Compression is what makes Baichuan-Omni-1.5 fit smaller cards, at some cost in accuracy — IQ4_XS on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for Baichuan-Omni-1.5 follows memory bandwidth, not core counts, which is why the B200 tops it at 308 tok/s.
05

Read the fit column last

Tight means Baichuan-Omni-1.5 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

Following a card through to its own page shows every other model it can hold, which is the question that follows once Baichuan-Omni-1.5 is settled.

Answers

Baichuan-Omni-1.5 — common questions

Is Baichuan-Omni-1.5 open source?

Its weights are published, so Baichuan-Omni-1.5 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-Omni-1.5 have?

Baichuan-Omni-1.5 has 11B parameters. Safetensors: 11B params. 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-Omni-1.5?

Baichuan-Omni-1.5 was published by Baichuan, based in China, categorised as industry.

When was Baichuan-Omni-1.5 released?

Baichuan-Omni-1.5 was published in January 2025.

What is Baichuan-Omni-1.5 used for?

Baichuan-Omni-1.5 works in Multimodal, Language, Speech, Vision, Video, Audio, and is recorded as handling language modeling/generation, Question answering, Audio question answering, Speech recognition (ASR), Speech-to-text, Visual question answering, Image captioning, Speech synthesis, Text-to-speech (TTS), Video, Video classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Baichuan-Omni-1.5?

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-Omni-1.5?

Around 3.3 × 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-Omni-1.5 if it does not fit in my GPU?

It can be split between the card and system memory, but Baichuan-Omni-1.5 generates painfully slowly that way — the nearest miss we calculate is short by 2.0 GB. Nothing on this page assumes offloading.

Would two GPUs run Baichuan-Omni-1.5 faster?

Two cards buy memory rather than speed. That matters for Baichuan-Omni-1.5 only if one card cannot hold it — 509 can, so a second adds little.

Why does the quantisation differ between cards for Baichuan-Omni-1.5?

Because capacity varies, so does how hard Baichuan-Omni-1.5 has to be squeezed — 4 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Baichuan-Omni-1.5 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 185–493 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 Baichuan-Omni-1.5?

The smallest card in our catalogue that holds Baichuan-Omni-1.5 is the Xeon Phi 5110P, with 8 GB of memory. It runs the model at IQ4_XS using about 6.7 GB, and produces roughly 19.7 tokens per second. 509 cards in total can run it.

How fast is Baichuan-Omni-1.5 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 308 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 460 of the cards that can run Baichuan-Omni-1.5 clear that.

How much VRAM does Baichuan-Omni-1.5 need?

About 6.7 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 Baichuan-Omni-1.5 on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at IQ4_XS, using about 6.7 GB and generating roughly 141 tokens per second — a tight fit.

Can I run Baichuan-Omni-1.5 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q6_K, using about 9.9 GB and generating roughly 51.0 tokens per second — a tight fit.

Can I run Baichuan-Omni-1.5 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 12.5 GB and generating roughly 43.5 tokens per second — a tight fit.

Can I run Baichuan-Omni-1.5 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 12.5 GB and generating roughly 51.6 tokens per second — a comfortable fit.

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