Typhoon2-Audio TPS calculator

Open weights Typhoon / SCB 10X 9.7B parameters December 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

509 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 5110P

8 GB · Q4_K_M · 21.0 tok/s

Fastest card

B200

350 tok/s · 180 GB

Which GPUs can run Typhoon2-Audio?

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
350 tok/s 210–560 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	11.1 GB	Q8_0	Comfortable
350 tok/s 210–560 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	11.1 GB	Q8_0	Comfortable
279 tok/s 168–447 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	11.1 GB	Q8_0	Comfortable
279 tok/s 168–447 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	11.1 GB	Q8_0	Comfortable
223 tok/s 134–357 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	11.1 GB	Q8_0	Comfortable
214 tok/s 128–342 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	11.1 GB	Q8_0	Comfortable
214 tok/s 128–342 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	11.1 GB	Q8_0	Comfortable
205 tok/s 123–327 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	11.1 GB	Q8_0	Comfortable
182 tok/s 109–291 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	11.1 GB	Q8_0	Comfortable
182 tok/s 109–291 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	11.1 GB	Q8_0	Comfortable
182 tok/s 109–291 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	11.1 GB	Q8_0	Comfortable
172 tok/s 103–276 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	11.1 GB	Q8_0	Comfortable
150 tok/s 90–241 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.6 GB	Q4_K_M	Tight
147 tok/s 88–235 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	11.1 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	11.1 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	11.1 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	11.1 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	11.1 GB	Q8_0	Comfortable
112 tok/s 67–179 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	11.1 GB	Q8_0	Comfortable
112 tok/s 67–179 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	11.1 GB	Q8_0	Comfortable
99.1 tok/s 59–159 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.8 GB	Q6_K	Tight
93.2 tok/s 56–149 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	11.1 GB	Q8_0	Comfortable
91.2 tok/s 55–146 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	11.1 GB	Q8_0	Comfortable
89.2 tok/s 54–143 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	11.1 GB	Q8_0	Comfortable
89.2 tok/s 54–143 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	11.1 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: Typhoon / SCB 10X
Organisation type: Industry
Country: Thailand
Published: 19 December 2024
Authors: Kunat Pipatanakul, Potsawee Manakul, Natapong Nitarach, Warit Sirichotedumrong, Surapon Nonesung, Teetouch Jaknamon, Parinthapat Pengpun, Pittawat Taveekitworachai, Adisai Na-Thalang, Sittipong Sripaisarnmongkol, Krisanapong Jirayoot, Kasima Tharnpipitchai

What it does

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

Domain: Audio, Language, Speech, Multimodal
Task: Language modeling/generation, Speech synthesis, Speech recognition (ASR), Text-to-speech (TTS), Audio generation, Audio question answering, Translation, Speech-to-speech
Base model: Llama 3.1 Typhoon 2 8B

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: 9.7B
Training data: tokens

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: scb10x

How it is classified

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

Record confidence: Confident

Sources

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

Reference: Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Typhoon2-Audio

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 Typhoon2-Audio

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

Xeon Phi 5110P

Memory needed

6.6 GB

Fastest

350 tok/s

Typhoon2-Audio reaches a parameter count of 9.7B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 509.

The smallest card that holds it is Xeon Phi 5110P, with a memory capacity of 8 GB, running it at a compression of Q4_K_M and producing around 21.0 tokens per second.

Top of the range is B200, generating roughly 350 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

Typhoon2-Audio was published by Typhoon / SCB 10X, in the country recorded as Thailand, during December 2024. The publishing organisation is categorised as industry.

It works in the domain of Audio, Language, Speech, Multimodal, and is recorded as performing the task of language modeling/generation, Speech synthesis, Speech recognition (ASR), Text-to-speech (TTS), Audio generation, Audio question answering, Translation, Speech-to-speech.

Rather than being trained from scratch, it is derived from Llama 3.1 Typhoon 2 8B. Most models at this scale are adapted from an existing base rather than built from nothing.

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. On Hugging Face it is published under the organisation scb10x.

What decides the speed

Across every card that can run it, the middle of the range sits at 22.7 tokens per second. Exceeding reading speed outright: 471 of them.

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.

Step by step

How to choose a GPU for Typhoon2-Audio

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

Start from what it actually needs, which is the requirement of Typhoon2-Audio, needing around 6.6 GB at a compression of Q4_K_M. Capacity is the gate — a card either holds it or it does not.
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, because at long context a card that handles short questions easily can be dropped by Typhoon2-Audio.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of Q4_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for Typhoon2-Audio. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 350 tok/s.
05

Check the fit verdict before buying

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Typhoon2-Audio. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
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 you have settled on Typhoon2-Audio.

Answers

Typhoon2-Audio — common questions

Typhoon2-Audio— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 210–560 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Typhoon2-Audio— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Xeon Phi 5110P, with a memory capacity of 8 GB. It runs the model at a compression of Q4_K_M using about 6.6 GB, and produces roughly 21.0 tokens per second. The number of cards able to run it in total: 509.

Typhoon2-Audio— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 350 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 471.

Typhoon2-Audio— how much VRAM does it need?

It needs about 6.6 GB at a compression of Q4_K_M, 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.

Typhoon2-Audio— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q4_K_M, using about 6.6 GB and generating roughly 150 tokens per second. The fit is tight.

Typhoon2-Audio— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q6_K, using about 8.8 GB and generating roughly 58.0 tokens per second. The fit is comfortable.

Typhoon2-Audio— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q8_0, using about 11.1 GB and generating roughly 49.4 tokens per second. The fit is comfortable.

Typhoon2-Audio— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q8_0, using about 11.1 GB and generating roughly 58.6 tokens per second. The fit is comfortable.

Typhoon2-Audio— is it open source?

Its weights are published, so it 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.

Typhoon2-Audio— how many parameters does it have?

It has a parameter count of 9.7B. Table 26: 9.688B. 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.

Typhoon2-Audio— who created it?

It was published by Typhoon / SCB 10X, based in Thailand, an organisation categorised as industry.

Typhoon2-Audio— when was it released?

It was published in December 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.

Typhoon2-Audio— what is it used for?

It works in the domain of Audio, Language, Speech, Multimodal, and is recorded as handling the task of language modeling/generation, Speech synthesis, Speech recognition (ASR), Text-to-speech (TTS), Audio generation, Audio question answering, Translation, Speech-to-speech. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Typhoon2-Audio— where can I download it?

Its weights are published on Hugging Face, under the organisation scb10x. We do not host model files — this site calculates what hardware is needed to run them.

Typhoon2-Audio— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 1.2 GB. Every figure here assumes the whole model is resident on the card.

Typhoon2-Audio— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 509. So a second card is rarely the answer here.

Typhoon2-Audio— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 3. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

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