INTELLECT-3 TPS calculator

Open weights Prime Intellect 106B parameters November 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

43 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI200

64 GB · IQ4_XS · 69.7 tok/s

Fastest card

B200

178 tok/s · 180 GB

Which GPUs can run INTELLECT-3?

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

43 cards match

Calculating

					Needs	Quantisation	Fit
178 tok/s 107–284 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	108.8 GB	Q8_0	Comfortable
178 tok/s 107–284 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	108.8 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	108.8 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	108.8 GB	Q8_0	Comfortable
133 tok/s 80–213 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	71.8 GB	Q5_K_M	Tight
133 tok/s 80–213 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	71.8 GB	Q5_K_M	Tight
127 tok/s 76–203 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	84.1 GB	Q6_K	Tight
113 tok/s 68–181 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	108.8 GB	Q8_0	Tight
110 tok/s 66–176 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	53.3 GB	IQ4_XS	Tight
109 tok/s 65–174 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	108.8 GB	Q8_0	Tight
109 tok/s 65–174 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	108.8 GB	Q8_0	Tight
108 tok/s 65–173 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	84.1 GB	Q6_K	Tight
108 tok/s 65–173 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	84.1 GB	Q6_K	Tight
108 tok/s 65–173 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	84.1 GB	Q6_K	Tight
104 tok/s 62–166 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	108.8 GB	Q8_0	Comfortable
92.2 tok/s 55–148 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	108.8 GB	Q8_0	Tight
92.2 tok/s 55–148 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	108.8 GB	Q8_0	Comfortable
92.2 tok/s 55–148 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	108.8 GB	Q8_0	Comfortable
80.9 tok/s 49–129 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	71.8 GB	Q5_K_M	Tight
80.9 tok/s 49–129 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	71.8 GB	Q5_K_M	Tight
80.9 tok/s 49–129 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	71.8 GB	Q5_K_M	Tight
80.9 tok/s 49–129 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	71.8 GB	Q5_K_M	Tight
80.9 tok/s 49–129 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	71.8 GB	Q5_K_M	Tight
80.9 tok/s 49–129 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	71.8 GB	Q5_K_M	Tight
76.9 tok/s 46–123 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	71.8 GB	Q5_K_M	Tight

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: Prime Intellect
Organisation type: Industry
Country: United States of America
Published: 26 November 2025
Authors: Mika Senghaas, Fares Obeid, Sami Jaghouar, William Brown, Jack Min Ong, Daniel Auras, Matej Sirovatka, Jannik Straube, Andrew Baker, Sebastian Müller, Justus Mattern, Manveer Basra, Aiman Ismail, Dominik Scherm, Cooper Miller, Ameen Patel, Simon Kirsten, Mario Sieg, Christian Reetz, Kemal Erdem, Vincent Weisser, Johannes Hagemann

What it does

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

Domain: Language
Task: Language modeling/generation
Base model: GLM-4.5-Air

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: 106B
Training data: tokens

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 H200
Wall-clock time: 1,440 hours (60 days)

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)
Hugging Face: PrimeIntellect

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: INTELLECT-3: Technical Report
Last updated: 8 April 2026

The extremes

The ten fastest GPUs that run INTELLECT-3

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 INTELLECT-3

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

Radeon Instinct MI200

Memory needed

53.3 GB

Fastest

178 tok/s

INTELLECT-3 reaches a parameter count of 106B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 43.

The smallest card that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB, running it at a compression of IQ4_XS and producing around 69.7 tokens per second.

At the other end sits B200, generating roughly 178 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

INTELLECT-3 was published by Prime Intellect, in the country recorded as United States of America, during November 2025. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation.

Its starting point was an existing base model, GLM-4.5-Air. That is why it shares the base model's general shape and size.

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

How fast it runs, and why

The median result is around 80.9 tokens per second. Producing text faster than most people read it: 41 of them.

This is a mixture-of-experts model, which routes each token through only part of itself. It therefore generates far faster than its total size suggests — while still needing every parameter resident in memory, so it is quick without being cheap to hold.

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 INTELLECT-3

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 able to hold INTELLECT-3, needing around 53.3 GB at a compression of IQ4_XS. That figure, not the headline performance of a card, is what decides whether it runs.
02

Match the context to your actual use

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting INTELLECT-3.
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 IQ4_XS 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

Compare tokens per second, not specifications

Ranking by tokens per second follows memory bandwidth rather than core counts, for INTELLECT-3. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 178 tok/s.
05

Check the fit verdict before buying

Tight means it loads and works with no room to raise the context later, in the case of INTELLECT-3. 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

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. A card is usually bought for more than one model, so it is worth a look before buying for INTELLECT-3.

Answers

INTELLECT-3 — common questions

INTELLECT-3— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 43. So a second card is rarely the answer here.

INTELLECT-3— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

INTELLECT-3— 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: 107–284 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

INTELLECT-3— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB. It runs the model at a compression of IQ4_XS using about 53.3 GB, and produces roughly 69.7 tokens per second. The number of cards able to run it in total: 43.

INTELLECT-3— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 178 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: 41.

INTELLECT-3— how much VRAM does it need?

It needs about 53.3 GB at a compression of IQ4_XS, 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.

INTELLECT-3— 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.

INTELLECT-3— how many parameters does it have?

It has a parameter count of 106B. "We present INTELLECT-3, a 106B-parameter Mixture-of-Experts model (12B active)". 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.

INTELLECT-3— who created it?

It was published by Prime Intellect, based in United States of America, an organisation categorised as industry.

INTELLECT-3— when was it released?

It was published in November 2025.

INTELLECT-3— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

INTELLECT-3— where can I download it?

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

INTELLECT-3— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 16.3 GB. Every figure here assumes the whole model is resident on the card.

Source

Original publication

Record last updated 8 April 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