Eurus-2-7B-PRIME TPS calculator

Open weights Shanghai AI Lab,Tsinghua University,University of Illinois Urbana-Champaign (UIUC),Peking University,Shanghai Jiao Tong University,Chinese University of Hong Kong (CUHK) 7B parameters February 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

589 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla K20c

5 GB · Q3_K_M · 28.9 tok/s

Fastest card

B200

484 tok/s · 180 GB

Which GPUs can run Eurus-2-7B-PRIME?

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

589 cards match

Calculating

					Needs	Quantisation	Fit
484 tok/s 290–774 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.2 GB	Q8_0	Comfortable
484 tok/s 290–774 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.2 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.2 GB	Q8_0	Comfortable
387 tok/s 232–618 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.2 GB	Q8_0	Comfortable
309 tok/s 185–495 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.2 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.2 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.2 GB	Q8_0	Comfortable
283 tok/s 170–453 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.2 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
251 tok/s 151–402 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.2 GB	Q8_0	Comfortable
238 tok/s 143–381 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
203 tok/s 122–325 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.2 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.2 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.2 GB	Q8_0	Comfortable
131 tok/s 79–210 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.6 GB	Q6_K	Tight
129 tok/s 77–206 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.2 GB	Q8_0	Comfortable
126 tok/s 76–202 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.2 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.2 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.2 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.2 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: Shanghai AI Lab,Tsinghua University,University of Illinois Urbana-Champaign (UIUC),Peking University,Shanghai Jiao Tong University,Chinese University of Hong Kong (CUHK)
Organisation type: Academia,Academia,Academia,Academia,Academia,Academia
Country: China, United States of America, Hong Kong
Published: 3 February 2025
Authors: Ganqu Cui, Lifan Yuan, Zefan Wang, Hanbin Wang, Yuchen Zhang, Jiacheng Chen, Wendi Li, Bingxiang He, Yuchen Fan, Tianyu Yu, Qixin Xu, Weize Chen, Jiarui Yuan, Huayu Chen, Kaiyan Zhang, Xingtai Lv, Shuo Wang, Yuan Yao, Xu Han, Hao Peng, Yu Cheng, Zhiyuan Liu, Maosong Sun, Bowen Zhou, Ning Ding

What it does

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

Domain: Language
Task: Mathematical problem solving, Mathematical reasoning, Language modeling/generation
Approach: Reinforcement learning,Supervised fine-tuning (SFT)
Base model: Qwen2.5-Math-7B-Base

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: 7B
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: 4 × 10²⁰ FLOP
Fine-tuning compute: 1.3 × 10¹⁸ FLOP

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 PCIe 80 GB
Chips used: 8
Power draw: 3.9 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 (restricted use)
Hugging Face: PRIME-RL

How it is classified

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

Record confidence: Likely
Citations: 333

Sources

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

Reference: Process Reinforcement through Implicit Rewards
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Eurus-2-7B-PRIME

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 Eurus-2-7B-PRIME

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

Tesla K20c

Memory needed

4.1 GB

Fastest

484 tok/s

Eurus-2-7B-PRIME reaches a parameter count of 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: 589.

At the low end it is handled by Tesla K20c, with a memory capacity of 5 GB, running it at a compression of Q3_K_M and producing around 28.9 tokens per second.

At the other end sits B200, generating roughly 484 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

Eurus-2-7B-PRIME was published by Shanghai AI Lab,Tsinghua University,University of Illinois Urbana-Champaign (UIUC),Peking University,Shanghai Jiao Tong University,Chinese University of Hong Kong (CUHK), in the country recorded as China, during February 2025. It comes out of an organisation categorised as academia,Academia,Academia,Academia,Academia,Academia.

It works in the domain of Language, and is recorded as performing the task of mathematical problem solving, Mathematical reasoning, Language modeling/generation.

It builds on Qwen2.5-Math-7B-Base. 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. On Hugging Face it is published under the organisation PRIME-RL.

Reading the throughput figures

Half the cards that hold it manage more than 26.1 tokens per second. Exceeding reading speed outright: 559 of them.

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.

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.

What went into building it

Producing it required arithmetic totalling around 4 × 10²⁰ FLOP, on hardware recorded as NVIDIA A800 PCIe 80 GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Step by step

How to choose a GPU for Eurus-2-7B-PRIME

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

Start from what it actually needs, which is the requirement of Eurus-2-7B-PRIME, needing around 4.1 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Eurus-2-7B-PRIME.
03

Decide how much compression you will accept

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q3_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

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for Eurus-2-7B-PRIME. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 484 tok/s.
05

Look at the headroom, not just the fit

Tight means it loads and works with no room to raise the context later, in the case of Eurus-2-7B-PRIME. 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

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond Eurus-2-7B-PRIME.

Answers

Eurus-2-7B-PRIME — common questions

Eurus-2-7B-PRIME— 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: 589. So a second card is rarely the answer here.

Eurus-2-7B-PRIME— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Eurus-2-7B-PRIME— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 290–774 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Eurus-2-7B-PRIME— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Tesla K20c, with a memory capacity of 5 GB. It runs the model at a compression of Q3_K_M using about 4.1 GB, and produces roughly 28.9 tokens per second. The number of cards able to run it in total: 589.

Eurus-2-7B-PRIME— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 484 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: 559.

Eurus-2-7B-PRIME— how much VRAM does it need?

It needs about 4.1 GB at a compression of Q3_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.

Eurus-2-7B-PRIME— 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 Q6_K, using about 6.6 GB and generating roughly 131 tokens per second. The fit is tight.

Eurus-2-7B-PRIME— 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 Q8_0, using about 8.2 GB and generating roughly 55.2 tokens per second. The fit is comfortable.

Eurus-2-7B-PRIME— 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 8.2 GB and generating roughly 68.4 tokens per second. The fit is comfortable.

Eurus-2-7B-PRIME— 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 8.2 GB and generating roughly 81.1 tokens per second. The fit is comfortable.

Eurus-2-7B-PRIME— 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.

Eurus-2-7B-PRIME— how many parameters does it have?

It has a parameter count of 7B. 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.

Eurus-2-7B-PRIME— who created it?

It was published by Shanghai AI Lab,Tsinghua University,University of Illinois Urbana-Champaign (UIUC),Peking University,Shanghai Jiao Tong University,Chinese University of Hong Kong (CUHK), based in China, an organisation categorised as academia,Academia,Academia,Academia,Academia,Academia.

Eurus-2-7B-PRIME— when was it released?

It was published in February 2025.

Eurus-2-7B-PRIME— what is it used for?

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

Eurus-2-7B-PRIME— where can I download it?

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

Eurus-2-7B-PRIME— how much compute was used to train it?

Training consumed around 4 × 10²⁰ FLOP, on hardware recorded as NVIDIA A800 PCIe 80 GB. 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.

Eurus-2-7B-PRIME— 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 1.3 GB. Every figure here assumes the whole model is resident on the card.

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