TeleChat2-35B TPS calculator

Open weights China Telecom 35B parameters October 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 · 20.9 tok/s

Fastest card

B200

96.8 tok/s · 180 GB

Which GPUs can run TeleChat2-35B?

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
96.8 tok/s 58–155 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	38.2 GB	Q8_0	Comfortable
96.8 tok/s 58–155 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	38.2 GB	Q8_0	Comfortable
77.3 tok/s 46–124 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	38.2 GB	Q8_0	Comfortable
77.3 tok/s 46–124 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	38.2 GB	Q8_0	Comfortable
61.8 tok/s 37–99 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	38.2 GB	Q8_0	Comfortable
59.2 tok/s 36–95 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	38.2 GB	Q8_0	Comfortable
59.2 tok/s 36–95 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	38.2 GB	Q8_0	Comfortable
56.6 tok/s 34–91 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	38.2 GB	Q8_0	Comfortable
50.3 tok/s 30–80 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	38.2 GB	Q8_0	Comfortable
50.3 tok/s 30–80 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	38.2 GB	Q8_0	Comfortable
50.3 tok/s 30–80 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	38.2 GB	Q8_0	Comfortable
47.7 tok/s 29–76 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	38.2 GB	Q8_0	Comfortable
40.7 tok/s 24–65 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	38.2 GB	Q8_0	Comfortable
40.7 tok/s 24–65 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	38.2 GB	Q8_0	Comfortable
40.7 tok/s 24–65 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	38.2 GB	Q8_0	Comfortable
40.7 tok/s 24–65 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	38.2 GB	Q8_0	Comfortable
40.7 tok/s 24–65 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	38.2 GB	Q8_0	Comfortable
40.4 tok/s 24–65 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	25.9 GB	Q5_K_M	Tight
40.4 tok/s 24–65 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	25.9 GB	Q5_K_M	Tight
39.8 tok/s 24–64 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	19.8 GB	IQ4_XS	Tight
38.7 tok/s 23–62 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.9 GB	Q5_K_M	Tight
38.7 tok/s 23–62 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.9 GB	Q5_K_M	Tight
36.3 tok/s 22–58 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	19.8 GB	IQ4_XS	Tight
31.0 tok/s 19–50 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	38.2 GB	Q8_0	Comfortable
31.0 tok/s 19–50 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	38.2 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: China Telecom
Organisation type: Industry
Country: China
Published: 18 October 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, Quantitative reasoning, Chat, Text summarization, Code generation

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: 35B
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: Open (restricted use)

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: TeleChat2
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for TeleChat2-35B

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 TeleChat2-35B

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

RTX A4500

Memory needed

17.8 GB

Fastest

96.8 tok/s

With 35B parameters, TeleChat2-35B lands in the range a serious desktop card can handle once the weights are compressed. 132 of the cards we track can run it.

At the low end, a RTX A4500 handles it — 20 GB, at Q3_K_M, for about 20.9 tokens per second.

At the other end, a B200 generates roughly 96.8 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

About this model

TeleChat2-35B was published by China Telecom, in China, in October 2024. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Question answering, Quantitative reasoning, Chat, Text summarization, Code generation.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

How fast it runs, and why

Half the cards that hold it manage more than 20.6 tokens per second, and 103 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.

Step by step

How to choose a GPU for TeleChat2-35B

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

01

Start from the memory column

Every card here has been checked against TeleChat2-35B — around 17.8 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context TeleChat2-35B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of TeleChat2-35B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

Ranking by tokens per second for TeleChat2-35B follows memory bandwidth, not core counts, which is why the B200 tops it at 96.8 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs TeleChat2-35B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond TeleChat2-35B.

Answers

TeleChat2-35B — common questions

How much VRAM does TeleChat2-35B need?

About 17.8 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 TeleChat2-35B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at IQ4_XS, using about 19.8 GB and generating roughly 39.8 tokens per second — a tight fit.

Is TeleChat2-35B open source?

Its weights are published, so TeleChat2-35B 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 TeleChat2-35B have?

TeleChat2-35B has 35B 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 TeleChat2-35B?

TeleChat2-35B was published by China Telecom, based in China, categorised as industry.

When was TeleChat2-35B released?

TeleChat2-35B was published in October 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 TeleChat2-35B used for?

TeleChat2-35B works in Language, and is recorded as handling language modeling/generation, Question answering, Quantitative reasoning, Chat, Text summarization, Code generation. 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 TeleChat2-35B?

The weights for TeleChat2-35B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run TeleChat2-35B if it does not fit in my GPU?

It can be split between the card and system memory, but TeleChat2-35B generates painfully slowly that way — the nearest miss we calculate is short by 7.5 GB. Nothing on this page assumes offloading.

Would two GPUs run TeleChat2-35B faster?

Capacity adds across cards; throughput does not. Since 132 of the cards we track already hold TeleChat2-35B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for TeleChat2-35B?

Each card is shown running the least-compressed copy it can hold, and TeleChat2-35B appears at 6 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these TeleChat2-35B 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 58–155 tok/s on the B200 rather than a single number.

What GPU do I need to run TeleChat2-35B?

The smallest card in our catalogue that holds TeleChat2-35B is the RTX A4500, with 20 GB of memory. It runs the model at Q3_K_M using about 17.8 GB, and produces roughly 20.9 tokens per second. 132 cards in total can run it.

How fast is TeleChat2-35B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 96.8 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 TeleChat2-35B clear that.

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