Yi-1.5-9B TPS calculator

Open weights 01.AI 8.8B parameters May 2024

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 · Q3_K_M · 15.8 tok/s

Fastest card

B200

384 tok/s · 180 GB

Which GPUs can run Yi-1.5-9B?

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
384 tok/s 230–614 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	10.2 GB	Q8_0	Comfortable
384 tok/s 230–614 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	10.2 GB	Q8_0	Comfortable
306 tok/s 184–490 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	10.2 GB	Q8_0	Comfortable
306 tok/s 184–490 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	10.2 GB	Q8_0	Comfortable
245 tok/s 147–392 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	10.2 GB	Q8_0	Comfortable
235 tok/s 141–375 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	10.2 GB	Q8_0	Comfortable
235 tok/s 141–375 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	10.2 GB	Q8_0	Comfortable
224 tok/s 135–359 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	10.2 GB	Q8_0	Comfortable
199 tok/s 120–319 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	10.2 GB	Q8_0	Comfortable
199 tok/s 120–319 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	10.2 GB	Q8_0	Comfortable
199 tok/s 120–319 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	10.2 GB	Q8_0	Comfortable
189 tok/s 113–302 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	10.2 GB	Q8_0	Comfortable
161 tok/s 97–258 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	10.2 GB	Q8_0	Comfortable
161 tok/s 97–258 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	10.2 GB	Q8_0	Comfortable
161 tok/s 97–258 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	10.2 GB	Q8_0	Comfortable
161 tok/s 97–258 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	10.2 GB	Q8_0	Comfortable
161 tok/s 97–258 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	10.2 GB	Q8_0	Comfortable
128 tok/s 77–204 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	7.1 GB	Q5_K_M	Tight
123 tok/s 74–196 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	10.2 GB	Q8_0	Comfortable
123 tok/s 74–196 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	10.2 GB	Q8_0	Comfortable
109 tok/s 65–174 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.1 GB	Q6_K	Tight
102 tok/s 61–164 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	10.2 GB	Q8_0	Comfortable
100 tok/s 60–160 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	10.2 GB	Q8_0	Comfortable
97.9 tok/s 59–157 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	10.2 GB	Q8_0	Comfortable
97.9 tok/s 59–157 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	10.2 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: 01.AI
Organisation type: Industry
Country: China
Published: 13 May 2024

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, Chat

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: 8.8B
Training data: 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: 1.9 × 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: Unreleased
Hugging Face: 01-ai

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: Yi-1.5 is an upgraded version of Yi.
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Yi-1.5-9B

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 Yi-1.5-9B

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

5.0 GB

Fastest

384 tok/s

Yi-1.5-9B is small enough at 8.8B 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 Q3_K_M, for about 15.8 tokens per second.

At the other end, a B200 generates roughly 384 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

Yi-1.5-9B was published by 01.AI, in China, in May 2024. It comes out of industry.

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

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. It is published under the 01-ai organisation on Hugging Face.

Reading the throughput figures

The median result is around 21.6 tokens per second; 541 cards produce text faster than most people read it.

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.

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

Training it took roughly 1.9 × 10²³ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for Yi-1.5-9B

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

The table lists every card that can hold Yi-1.5-9B — around 5.0 GB at Q3_K_M. 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 Yi-1.5-9B stops fitting a card that seemed fine.
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 Yi-1.5-9B by squeezing it further than you would want.
04

Compare tokens per second, not specifications

The speed ordering for Yi-1.5-9B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 384 tok/s.
05

Read the fit column last

Tight means Yi-1.5-9B 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

Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for Yi-1.5-9B alone — a card is usually bought for more than one model.

Answers

Yi-1.5-9B — common questions

How many parameters does Yi-1.5-9B have?

Yi-1.5-9B has 8.8B parameters. 8.83B (safetensors). 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 Yi-1.5-9B?

Yi-1.5-9B was published by 01.AI, based in China, categorised as industry.

When was Yi-1.5-9B released?

Yi-1.5-9B was published in May 2024. 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 Yi-1.5-9B used for?

Yi-1.5-9B works in Language, and is recorded as handling language modeling/generation, Question answering, Chat. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Yi-1.5-9B?

Its weights are published under the 01-ai 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 Yi-1.5-9B?

Around 1.9 × 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 Yi-1.5-9B if it does not fit in my GPU?

It can be split between the card and system memory, but Yi-1.5-9B generates painfully slowly that way — the nearest miss we calculate is short by 1.5 GB. Nothing on this page assumes offloading.

Would two GPUs run Yi-1.5-9B faster?

A second card roughly doubles the memory available but not the generation rate. With 582 cards already able to run Yi-1.5-9B alone, the case for pairing is weak.

Why does the quantisation differ between cards for Yi-1.5-9B?

Because capacity varies, so does how hard Yi-1.5-9B has to be squeezed — 4 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Yi-1.5-9B speed estimates?

These are estimates with real error bars. The fastest result here, 230–614 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 Yi-1.5-9B?

The smallest card in our catalogue that holds Yi-1.5-9B is the Quadro 6000, with 6 GB of memory. It runs the model at Q3_K_M using about 5.0 GB, and produces roughly 15.8 tokens per second. 582 cards in total can run it.

How fast is Yi-1.5-9B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 384 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 541 of the cards that can run Yi-1.5-9B clear that.

How much VRAM does Yi-1.5-9B need?

About 5.0 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 Yi-1.5-9B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q5_K_M, using about 7.1 GB and generating roughly 128 tokens per second — a tight fit.

Can I run Yi-1.5-9B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 10.2 GB and generating roughly 43.8 tokens per second — a tight fit.

Can I run Yi-1.5-9B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 10.2 GB and generating roughly 54.2 tokens per second — a comfortable fit.

Can I run Yi-1.5-9B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 10.2 GB and generating roughly 64.3 tokens per second — a comfortable fit.

Is Yi-1.5-9B open source?

Its weights are published, so Yi-1.5-9B 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.

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