Incoder-6.7B TPS calculator

Open weights Facebook AI Research,University of Washington,University of California (UC) Berkeley,Carnegie Mellon University (CMU),Toyota Technological Institute at Chicago 6.7B parameters April 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

589 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla K20c

5 GB · IQ4_XS · 27.4 tok/s

Fastest card

B200

506 tok/s · 180 GB

Which GPUs can run Incoder-6.7B?

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
506 tok/s 303–809 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	7.9 GB	Q8_0	Comfortable
506 tok/s 303–809 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	7.9 GB	Q8_0	Comfortable
404 tok/s 242–646 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	7.9 GB	Q8_0	Comfortable
404 tok/s 242–646 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	7.9 GB	Q8_0	Comfortable
323 tok/s 194–517 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	7.9 GB	Q8_0	Comfortable
309 tok/s 185–495 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	7.9 GB	Q8_0	Comfortable
309 tok/s 185–495 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	7.9 GB	Q8_0	Comfortable
296 tok/s 178–473 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	7.9 GB	Q8_0	Comfortable
263 tok/s 158–420 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	7.9 GB	Q8_0	Comfortable
263 tok/s 158–420 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	7.9 GB	Q8_0	Comfortable
263 tok/s 158–420 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	7.9 GB	Q8_0	Comfortable
249 tok/s 149–399 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	7.9 GB	Q8_0	Comfortable
212 tok/s 127–340 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	7.9 GB	Q8_0	Comfortable
212 tok/s 127–340 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	7.9 GB	Q8_0	Comfortable
212 tok/s 127–340 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	7.9 GB	Q8_0	Comfortable
212 tok/s 127–340 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	7.9 GB	Q8_0	Comfortable
212 tok/s 127–340 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	7.9 GB	Q8_0	Comfortable
162 tok/s 97–259 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	7.9 GB	Q8_0	Comfortable
162 tok/s 97–259 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	7.9 GB	Q8_0	Comfortable
137 tok/s 82–219 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.3 GB	Q6_K	Tight
135 tok/s 81–216 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	7.9 GB	Q8_0	Comfortable
132 tok/s 79–211 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	7.9 GB	Q8_0	Comfortable
129 tok/s 77–206 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	7.9 GB	Q8_0	Comfortable
129 tok/s 77–206 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	7.9 GB	Q8_0	Comfortable
129 tok/s 77–206 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	7.9 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: Facebook AI Research,University of Washington,University of California (UC) Berkeley,Carnegie Mellon University (CMU),Toyota Technological Institute at Chicago
Organisation type: Industry,Academia,Academia,Academia,Academia
Country: United States of America, France
Published: 9 April 2023
Authors: Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer, Mike Lewis

What it does

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

Domain: Language
Task: Code generation

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: 6.7B
Training data: 52,000,000,000 tokens
Epochs: 1

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: 3 × 10²¹ FLOP
How it was established: Reported

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 V100
Wall-clock time: 576 hours (24 days)
Compute cost: $3,129

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 (non-commercial)
Training code: Unreleased

How it is classified

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

Why it is tracked: SOTA improvement
Record confidence: Confident
Citations: 864

Sources

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

Reference: InCoder: A Generative Model for Code Infilling and Synthesis
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Incoder-6.7B

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 Incoder-6.7B

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 you need to run it

Minimum card

Tesla K20c

Memory needed

4.4 GB

Fastest

506 tok/s

Incoder-6.7B is small enough at 6.7B parameters that hardware is rarely the obstacle — 589 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla K20c. Its 5 GB is enough at IQ4_XS compression, giving roughly 27.4 tokens per second.

At the other end, a B200 generates roughly 506 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

Incoder-6.7B was published by Facebook AI Research,University of Washington,University of California (UC) Berkeley,Carnegie Mellon University (CMU),Toyota Technological Institute at Chicago, in United States of America, in April 2023. The organisation is categorised as industry,Academia,Academia,Academia,Academia.

It works in Language, and is recorded as doing code generation.

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.

Understanding the speeds

Half the cards that hold it manage more than 27.3 tokens per second, and 562 exceed reading speed outright.

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.

How it was trained

The training run consumed about 3 × 10²¹ FLOP, on NVIDIA V100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 52,000,000,000 tokens.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Step by step

How to choose a GPU for Incoder-6.7B

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

Look at what Incoder-6.7B actually needs — around 4.4 GB at IQ4_XS. No amount of processing power compensates for a card that cannot hold it.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Incoder-6.7B can slip off a card that handles short questions easily.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — IQ4_XS on the smallest card that fits. Setting a floor drops the cards that only manage Incoder-6.7B by squeezing it further than you would want.
04

Sort by speed

The speed ordering for Incoder-6.7B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 506 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage Incoder-6.7B from those with room to spare. Buy for the second if the context might grow.
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 Incoder-6.7B is settled.

Answers

Incoder-6.7B — common questions

Where can I download Incoder-6.7B?

The weights for Incoder-6.7B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

How much compute was used to train Incoder-6.7B?

Around 3 × 10²¹ FLOP, on NVIDIA V100. 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.

Can I run Incoder-6.7B if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded Incoder-6.7B is rarely worth using — the nearest miss we calculate is short by 1.2 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Incoder-6.7B faster?

Two cards buy memory rather than speed. That matters for Incoder-6.7B only if one card cannot hold it — 589 can, so a second adds little.

Why does the quantisation differ between cards for Incoder-6.7B?

A larger card holds a more accurate copy. Across the cards that run Incoder-6.7B, 4 compression levels are used; the floor control above pins it to one.

How accurate are these Incoder-6.7B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 303–809 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run Incoder-6.7B?

The smallest card in our catalogue that holds Incoder-6.7B is the Tesla K20c, with 5 GB of memory. It runs the model at IQ4_XS using about 4.4 GB, and produces roughly 27.4 tokens per second. 589 cards in total can run it.

How fast is Incoder-6.7B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 506 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 562 of the cards that can run Incoder-6.7B clear that.

How much VRAM does Incoder-6.7B need?

About 4.4 GB at IQ4_XS compression, 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.

Can I run Incoder-6.7B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q6_K, using about 6.3 GB and generating roughly 137 tokens per second — a tight fit.

Can I run Incoder-6.7B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 7.9 GB and generating roughly 57.7 tokens per second — a comfortable fit.

Can I run Incoder-6.7B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 7.9 GB and generating roughly 71.4 tokens per second — a comfortable fit.

Can I run Incoder-6.7B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 7.9 GB and generating roughly 84.7 tokens per second — a comfortable fit.

Is Incoder-6.7B open source?

Its weights are published, so Incoder-6.7B 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.

How many parameters does Incoder-6.7B have?

Incoder-6.7B has 6.7B parameters. 6.7B. 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.

Who created Incoder-6.7B?

Incoder-6.7B was published by Facebook AI Research,University of Washington,University of California (UC) Berkeley,Carnegie Mellon University (CMU),Toyota Technological Institute at Chicago, based in United States of America, categorised as industry,Academia,Academia,Academia,Academia.

When was Incoder-6.7B released?

Incoder-6.7B was published in April 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.

What is Incoder-6.7B used for?

Incoder-6.7B works in Language, and is recorded as handling code generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

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