Oryx 34B TPS calculator

Open weights Tsinghua University,Tencent,Nanyang Technological University 34B parameters September 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

132 of 818 cards that can run it

Smallest card that fits

RTX A4500

20 GB · Q3_K_M · 21.5 tok/s

Fastest card

B200

99.7 tok/s · 180 GB

Which GPUs can run Oryx 34B?

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

132 cards match

Calculating

					Needs	Quantisation	Fit
99.7 tok/s 60–159 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	37.1 GB	Q8_0	Comfortable
99.7 tok/s 60–159 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	37.1 GB	Q8_0	Comfortable
79.6 tok/s 48–127 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	37.1 GB	Q8_0	Comfortable
79.6 tok/s 48–127 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	37.1 GB	Q8_0	Comfortable
63.6 tok/s 38–102 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	37.1 GB	Q8_0	Comfortable
60.9 tok/s 37–97 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	37.1 GB	Q8_0	Comfortable
60.9 tok/s 37–97 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	37.1 GB	Q8_0	Comfortable
58.3 tok/s 35–93 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	37.1 GB	Q8_0	Comfortable
51.7 tok/s 31–83 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	37.1 GB	Q8_0	Comfortable
51.7 tok/s 31–83 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	37.1 GB	Q8_0	Comfortable
51.7 tok/s 31–83 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	37.1 GB	Q8_0	Comfortable
49.1 tok/s 29–79 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	37.1 GB	Q8_0	Comfortable
41.9 tok/s 25–67 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	37.1 GB	Q8_0	Comfortable
41.9 tok/s 25–67 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	37.1 GB	Q8_0	Comfortable
41.9 tok/s 25–67 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	37.1 GB	Q8_0	Comfortable
41.9 tok/s 25–67 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	37.1 GB	Q8_0	Comfortable
41.9 tok/s 25–67 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	37.1 GB	Q8_0	Comfortable
41.6 tok/s 25–67 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	25.2 GB	Q5_K_M	Tight
41.6 tok/s 25–67 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	25.2 GB	Q5_K_M	Tight
39.8 tok/s 24–64 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.2 GB	Q5_K_M	Tight
39.8 tok/s 24–64 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.2 GB	Q5_K_M	Tight
38.5 tok/s 23–62 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	21.3 GB	Q4_K_M	Tight
35.1 tok/s 21–56 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	21.3 GB	Q4_K_M	Tight
31.9 tok/s 19–51 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	37.1 GB	Q8_0	Comfortable
31.9 tok/s 19–51 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	37.1 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: Tsinghua University,Tencent,Nanyang Technological University
Organisation type: Academia,Industry,Academia
Country: China, Singapore
Published: 19 September 2024
Authors: Zuyan Liu, Yuhao Dong, Ziwei Liu, Winston Hu, Jiwen Lu, Yongming Rao

What it does

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

Domain: Multimodal, Vision, 3D modeling, Video, Language
Task: Visual question answering, Video compression, Image captioning, Video description, Language modeling/generation
Base model: Yi-1.5-34B

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: 34B
Training data: tokens
Batch size: 128

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware: NVIDIA A800 SXM
Chips used: 64
Power draw: 50.4 kW

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
Hugging Face: THUdyh

How it is classified

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

Why it is tracked: SOTA improvement
Record confidence: Confident
Citations: 161

Sources

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

Reference: Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
Last updated: 25 May 2026

The extremes

The ten fastest GPUs for Oryx 34B

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 Oryx 34B

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 it takes to run this model

Minimum card

RTX A4500

Memory needed

17.3 GB

Fastest

99.7 tok/s

With 34B parameters, Oryx 34B lands in the range a serious desktop card can handle once the weights are compressed. 132 of the cards we track can run it.

The smallest card that holds it is the RTX A4500 with 20 GB, running it at Q3_K_M and producing around 21.5 tokens per second.

Top of the range is the B200, at roughly 99.7 tokens per second thanks to 8,000 GB/s of bandwidth.

About this model

Oryx 34B was published by Tsinghua University,Tencent,Nanyang Technological University, in China, in September 2024. academia,Industry,Academia is the category the publisher falls under.

It works in Multimodal, Vision, 3D modeling, Video, Language, and is recorded as doing visual question answering, Video compression, Image captioning, Video description, Language modeling/generation.

Its starting point was Yi-1.5-34B — most models at this scale are adapted from an existing base rather than built from nothing.

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 THUdyh organisation on Hugging Face.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 21.2 tokens per second, and 103 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.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

How it was trained

Its inclusion criterion is sOTA improvement.

Step by step

How to choose a GPU for Oryx 34B

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 Oryx 34B actually needs — around 17.3 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Oryx 34B can slip off a card that handles short questions easily.
03

Choose how far you will compress it

Compression is what makes Oryx 34B fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Oryx 34B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 99.7 tok/s.
05

Read the fit column last

The fit column separates cards that just manage Oryx 34B from those with room to spare. Buy for the second if the context might grow.
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 Oryx 34B alone — a card is usually bought for more than one model.

Answers

Oryx 34B — common questions

When was Oryx 34B released?

Oryx 34B was published in September 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 Oryx 34B used for?

Oryx 34B works in Multimodal, Vision, 3D modeling, Video, Language, and is recorded as handling visual question answering, Video compression, Image captioning, Video description, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Oryx 34B?

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

Can I run Oryx 34B 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 Oryx 34B is rarely worth using — the nearest miss we calculate is short by 6.9 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Oryx 34B faster?

Two cards buy memory rather than speed. That matters for Oryx 34B only if one card cannot hold it — 132 can, so a second adds little.

Why does the quantisation differ between cards for Oryx 34B?

A larger card holds a more accurate copy. Across the cards that run Oryx 34B, 5 compression levels are used; the floor control above pins it to one.

How accurate are these Oryx 34B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 60–159 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 Oryx 34B?

The smallest card in our catalogue that holds Oryx 34B is the RTX A4500, with 20 GB of memory. It runs the model at Q3_K_M using about 17.3 GB, and produces roughly 21.5 tokens per second. 132 cards in total can run it.

How fast is Oryx 34B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 99.7 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 103 of the cards that can run Oryx 34B clear that.

How much VRAM does Oryx 34B need?

About 17.3 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 Oryx 34B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 21.3 GB and generating roughly 38.5 tokens per second — a tight fit.

Is Oryx 34B open source?

Its weights are published, so Oryx 34B 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 Oryx 34B have?

Oryx 34B has 34B 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 Oryx 34B?

Oryx 34B was published by Tsinghua University,Tencent,Nanyang Technological University, based in China, categorised as academia,Industry,Academia.

Source

Original publication

Record last updated 25 May 2026

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