GRITLM 7B TPS calculator

Open weights Contextual AI,The University of Hong Kong,Microsoft 7.2B parameters April 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

589 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla K20c

5 GB · Q3_K_M · 27.9 tok/s

Fastest card

B200

468 tok/s · 180 GB

Which GPUs can run GRITLM 7B?

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
468 tok/s 281–749 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	8.5 GB	Q8_0	Comfortable
468 tok/s 281–749 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	8.5 GB	Q8_0	Comfortable
374 tok/s 224–598 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	8.5 GB	Q8_0	Comfortable
374 tok/s 224–598 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	8.5 GB	Q8_0	Comfortable
299 tok/s 179–478 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	8.5 GB	Q8_0	Comfortable
286 tok/s 172–458 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.5 GB	Q8_0	Comfortable
286 tok/s 172–458 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	8.5 GB	Q8_0	Comfortable
274 tok/s 164–438 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	8.5 GB	Q8_0	Comfortable
243 tok/s 146–389 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	8.5 GB	Q8_0	Comfortable
243 tok/s 146–389 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	8.5 GB	Q8_0	Comfortable
243 tok/s 146–389 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	8.5 GB	Q8_0	Comfortable
230 tok/s 138–369 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	8.5 GB	Q8_0	Comfortable
197 tok/s 118–314 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.5 GB	Q8_0	Comfortable
197 tok/s 118–314 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	8.5 GB	Q8_0	Comfortable
197 tok/s 118–314 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	8.5 GB	Q8_0	Comfortable
197 tok/s 118–314 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	8.5 GB	Q8_0	Comfortable
197 tok/s 118–314 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	8.5 GB	Q8_0	Comfortable
150 tok/s 90–239 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	8.5 GB	Q8_0	Comfortable
150 tok/s 90–239 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	8.5 GB	Q8_0	Comfortable
127 tok/s 76–203 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.8 GB	Q6_K	Tight
125 tok/s 75–200 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	8.5 GB	Q8_0	Comfortable
122 tok/s 73–195 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	8.5 GB	Q8_0	Comfortable
119 tok/s 72–191 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	8.5 GB	Q8_0	Comfortable
119 tok/s 72–191 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	8.5 GB	Q8_0	Comfortable
119 tok/s 72–191 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	8.5 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: Contextual AI,The University of Hong Kong,Microsoft
Organisation type: Industry,Academia,Industry
Country: United States of America, Hong Kong
Published: 17 April 2024
Authors: Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, Douwe Kiela

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
Base model: Mistral 7B
Numerical format: BF16

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: 7.2B
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.

How it was established: Hardware
Fine-tuning compute: 1 × 10²¹ 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 A100 SXM4 80 GB
Chips used: 8
Chip-hours: 3,072
Wall-clock time: 48 hours
Power draw: 6.3 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

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: Generative Representational Instruction Tuning
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run GRITLM 7B

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 GRITLM 7B

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

Tesla K20c

Memory needed

4.2 GB

Fastest

468 tok/s

GRITLM 7B reaches a parameter count of 7.2B. 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.

The smallest card that holds it is Tesla K20c, with a memory capacity of 5 GB, running it at a compression of Q3_K_M and producing around 27.9 tokens per second.

The fastest we calculate for it is B200, generating roughly 468 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

GRITLM 7B was published by Contextual AI,The University of Hong Kong,Microsoft, in the country recorded as United States of America, during April 2024. The publishing organisation is categorised as industry,Academia,Industry.

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

It builds on Mistral 7B. That is the usual way a specialised model is produced.

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.

What decides the speed

The median result is around 25.3 tokens per second. Producing text faster than most people read it: 559 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.

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 GRITLM 7B

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

The table lists every card able to hold GRITLM 7B, needing around 4.2 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for GRITLM 7B.
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 GRITLM 7B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 468 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 GRITLM 7B. 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 GRITLM 7B.

Answers

GRITLM 7B — common questions

GRITLM 7B— who created it?

It was published by Contextual AI,The University of Hong Kong,Microsoft, based in United States of America, an organisation categorised as industry,Academia,Industry.

GRITLM 7B— when was it released?

It was published in April 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.

GRITLM 7B— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering, Quantitative reasoning. 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.

GRITLM 7B— where can I download it?

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

GRITLM 7B— 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 1.5 GB. Every figure here assumes the whole model is resident on the card.

GRITLM 7B— 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.

GRITLM 7B— 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.

GRITLM 7B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 281–749 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

GRITLM 7B— 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 4.2 GB, and produces roughly 27.9 tokens per second. The number of cards able to run it in total: 589.

GRITLM 7B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 468 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.

GRITLM 7B— how much VRAM does it need?

It needs about 4.2 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.

GRITLM 7B— 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 6.8 GB and generating roughly 127 tokens per second. The fit is tight.

GRITLM 7B— 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 8.5 GB and generating roughly 53.4 tokens per second. The fit is comfortable.

GRITLM 7B— 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 8.5 GB and generating roughly 66.1 tokens per second. The fit is comfortable.

GRITLM 7B— 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 8.5 GB and generating roughly 78.4 tokens per second. The fit is comfortable.

GRITLM 7B— 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.

GRITLM 7B— how many parameters does it have?

It has a parameter count of 7.2B. 7.24B. 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.

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