DeciLM 6B TPS calculator

Open weights Deci AI 5.7B parameters September 2023

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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q3_K_M · 17.5 tok/s

Fastest card

B200

594 tok/s · 180 GB

Which GPUs can run DeciLM 6B?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
594 tok/s 357–951 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	6.8 GB	Q8_0	Comfortable
594 tok/s 357–951 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	6.8 GB	Q8_0	Comfortable
475 tok/s 285–759 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	6.8 GB	Q8_0	Comfortable
475 tok/s 285–759 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	6.8 GB	Q8_0	Comfortable
380 tok/s 228–607 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	6.8 GB	Q8_0	Comfortable
363 tok/s 218–581 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	6.8 GB	Q8_0	Comfortable
363 tok/s 218–581 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	6.8 GB	Q8_0	Comfortable
348 tok/s 209–556 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	6.8 GB	Q8_0	Comfortable
309 tok/s 185–494 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	6.8 GB	Q8_0	Comfortable
309 tok/s 185–494 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	6.8 GB	Q8_0	Comfortable
309 tok/s 185–494 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	6.8 GB	Q8_0	Comfortable
293 tok/s 176–468 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	6.8 GB	Q8_0	Comfortable
250 tok/s 150–399 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	6.8 GB	Q8_0	Comfortable
250 tok/s 150–399 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	6.8 GB	Q8_0	Comfortable
250 tok/s 150–399 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	6.8 GB	Q8_0	Comfortable
250 tok/s 150–399 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	6.8 GB	Q8_0	Comfortable
250 tok/s 150–399 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	6.8 GB	Q8_0	Comfortable
190 tok/s 114–304 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	6.8 GB	Q8_0	Comfortable
190 tok/s 114–304 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	6.8 GB	Q8_0	Comfortable
158 tok/s 95–253 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	6.8 GB	Q8_0	Comfortable
155 tok/s 93–248 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	6.8 GB	Q8_0	Comfortable
152 tok/s 91–243 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	6.8 GB	Q8_0	Comfortable
152 tok/s 91–243 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	6.8 GB	Q8_0	Comfortable
152 tok/s 91–243 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	6.8 GB	Q8_0	Comfortable
152 tok/s 91–243 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	6.8 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: Deci AI
Organisation type: Industry
Country: Israel
Published: 13 September 2023
Authors: DeciAI Research Team

What it does

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

Domain: Language
Task: Chat

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: 5.7B
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: 1 × 10²² FLOP
How it was established: Operation counting

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: Unreleased

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: DeciLM 6B
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run DeciLM 6B

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 DeciLM 6B

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 C1080

Memory needed

3.5 GB

Fastest

594 tok/s

DeciLM 6B reaches a parameter count of 5.7B. 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: 818.

The smallest card that holds it is Tesla C1080, with a memory capacity of 4 GB, running it at a compression of Q3_K_M and producing around 17.5 tokens per second.

The fastest we calculate for it is B200, generating roughly 594 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

DeciLM 6B was published by Deci AI, in the country recorded as Israel, during September 2023. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of chat.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

Reading the throughput figures

The median result is around 25.2 tokens per second. Producing text faster than most people read it: 759 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.

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.

How it was trained

Producing it required arithmetic totalling around 1 × 10²² FLOP. 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 DeciLM 6B

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 DeciLM 6B, needing around 3.5 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 DeciLM 6B.
03

Set a quality floor

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

Compare tokens per second, not specifications

Sort by speed to see how cards rank for DeciLM 6B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 594 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 DeciLM 6B. 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

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 DeciLM 6B.

Answers

DeciLM 6B — common questions

DeciLM 6B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Tesla C1080, with a memory capacity of 4 GB. It runs the model at a compression of Q3_K_M using about 3.5 GB, and produces roughly 17.5 tokens per second. The number of cards able to run it in total: 818.

DeciLM 6B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 594 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: 759.

DeciLM 6B— how much VRAM does it need?

It needs about 3.5 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.

DeciLM 6B— 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 Q8_0, using about 6.8 GB and generating roughly 111 tokens per second. The fit is tight.

DeciLM 6B— 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 6.8 GB and generating roughly 67.8 tokens per second. The fit is comfortable.

DeciLM 6B— 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 6.8 GB and generating roughly 84.0 tokens per second. The fit is comfortable.

DeciLM 6B— 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 6.8 GB and generating roughly 99.6 tokens per second. The fit is comfortable.

DeciLM 6B— 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.

DeciLM 6B— how many parameters does it have?

It has a parameter count of 5.7B. "DeciLM 6B is a 5.7 billion parameter decoder-only text generation model. ". 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.

DeciLM 6B— who created it?

It was published by Deci AI, based in Israel, an organisation categorised as industry.

DeciLM 6B— when was it released?

It was published in September 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

DeciLM 6B— what is it used for?

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

DeciLM 6B— 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.

DeciLM 6B— how much compute was used to train it?

Training consumed around 1 × 10²² FLOP. 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.

DeciLM 6B— 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. Every figure here assumes the whole model is resident on the card.

DeciLM 6B— 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: 818. So a second card is rarely the answer here.

DeciLM 6B— 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: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

DeciLM 6B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 357–951 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

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