GRITLM 8x7B TPS calculator

Open weights Contextual AI,The University of Hong Kong,Microsoft 46.7B 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

93 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon PRO V710

28 GB · Q3_K_M · 9.6 tok/s

Fastest card

B200

72.6 tok/s · 180 GB

Which GPUs can run GRITLM 8x7B?

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

93 cards match

Calculating

					Needs	Quantisation	Fit
72.6 tok/s 44–116 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	50.7 GB	Q8_0	Comfortable
72.6 tok/s 44–116 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	50.7 GB	Q8_0	Comfortable
57.9 tok/s 35–93 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	50.7 GB	Q8_0	Comfortable
57.9 tok/s 35–93 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	50.7 GB	Q8_0	Comfortable
46.3 tok/s 28–74 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	50.7 GB	Q8_0	Comfortable
44.4 tok/s 27–71 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	50.7 GB	Q8_0	Comfortable
44.4 tok/s 27–71 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	50.7 GB	Q8_0	Comfortable
42.4 tok/s 25–68 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	50.7 GB	Q8_0	Comfortable
41.6 tok/s 25–67 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	26.2 GB	IQ4_XS	Tight
41.6 tok/s 25–67 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	26.2 GB	IQ4_XS	Tight
39.9 tok/s 24–64 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	26.2 GB	IQ4_XS	Tight
39.9 tok/s 24–64 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	26.2 GB	IQ4_XS	Tight
37.7 tok/s 23–60 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	50.7 GB	Q8_0	Comfortable
37.7 tok/s 23–60 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	50.7 GB	Q8_0	Comfortable
37.7 tok/s 23–60 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	50.7 GB	Q8_0	Comfortable
35.7 tok/s 21–57 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	50.7 GB	Q8_0	Comfortable
30.5 tok/s 18–49 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	50.7 GB	Q8_0	Comfortable
30.5 tok/s 18–49 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	50.7 GB	Q8_0	Comfortable
30.5 tok/s 18–49 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	50.7 GB	Q8_0	Comfortable
30.5 tok/s 18–49 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	50.7 GB	Q8_0	Comfortable
30.5 tok/s 18–49 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	50.7 GB	Q8_0	Comfortable
25.3 tok/s 15–40 · low confidence	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	34.4 GB	Q5_K_M	Tight
25.3 tok/s 15–40 · low confidence	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	34.4 GB	Q5_K_M	Tight
25.3 tok/s 15–40 · low confidence	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	34.4 GB	Q5_K_M	Tight
25.2 tok/s 15–40 · low confidence	Tesla PG500-216 NVIDIA	32 GB	1,130 GB/s	Nov 2019	26.2 GB	IQ4_XS	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: 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: Mixtral 8x7B
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: 46.7B
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.

How it was established: Hardware
Fine-tuning compute: 2.2 × 10²² 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 H100 SXM5 80GB
Chips used: 8
Chip-hours: 20,480
Wall-clock time: 80 hours
Power draw: 11.1 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 8x7B

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 8x7B

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 you need to run it

Minimum card

Radeon PRO V710

Memory needed

23.5 GB

Fastest

72.6 tok/s

GRITLM 8x7B reaches a parameter count of 46.7B. That lands in the range a serious desktop card can handle once the weights are compressed. The number of cards we track that can run it: 93.

The least hardware that works is Radeon PRO V710, with a memory capacity of 28 GB, running it at a compression of Q3_K_M and producing around 9.6 tokens per second.

At the other end sits B200, generating roughly 72.6 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

GRITLM 8x7B 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.

Rather than being trained from scratch, it is derived from Mixtral 8x7B. That is why it shares the base model's general shape and size.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold.

How fast it runs, and why

Half the cards that hold it manage more than 18.3 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 74 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.

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.

Step by step

How to choose a GPU for GRITLM 8x7B

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 GRITLM 8x7B, needing around 23.5 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
02

Decide how long your conversations run

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 GRITLM 8x7B.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy, 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

Sort by speed

Ranking by tokens per second follows memory bandwidth rather than core counts, for GRITLM 8x7B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 72.6 tok/s.
05

Read the fit column last

Tight means it loads and works with no room to raise the context later, in the case of GRITLM 8x7B. 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

Open the card you have settled on

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 8x7B.

Answers

GRITLM 8x7B — common questions

GRITLM 8x7B— 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 8x7B— 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. These are the areas it was designed around; they describe intent rather than a hard boundary.

GRITLM 8x7B— 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 8x7B— 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 7.4 GB. Every figure here assumes the whole model is resident on the card.

GRITLM 8x7B— 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: 93. So a second card is rarely the answer here.

GRITLM 8x7B— 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: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

GRITLM 8x7B— 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: 44–116 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 8x7B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon PRO V710, with a memory capacity of 28 GB. It runs the model at a compression of Q3_K_M using about 23.5 GB, and produces roughly 9.6 tokens per second. The number of cards able to run it in total: 93.

GRITLM 8x7B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 72.6 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: 74.

GRITLM 8x7B— how much VRAM does it need?

It needs about 23.5 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 8x7B— 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 8x7B— how many parameters does it have?

It has a parameter count of 46.7B. 46.7B. 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.

GRITLM 8x7B— 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.

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