StarCoder 2 15B TPS calculator

Open weights Hugging Face,ServiceNow,NVIDIA,BigCode 15B parameters February 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

306 cards that can run it

818 cards we hold specifications for

Smallest card that fits

P102-101

10 GB · IQ4_XS · 18.9 tok/s

Fastest card

B200

226 tok/s · 180 GB

Which GPUs can run StarCoder 2 15B?

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

306 cards match

Calculating

					Needs	Quantisation	Fit
226 tok/s 136–361 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	16.8 GB	Q8_0	Comfortable
226 tok/s 136–361 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	16.8 GB	Q8_0	Comfortable
180 tok/s 108–289 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	16.8 GB	Q8_0	Comfortable
180 tok/s 108–289 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	16.8 GB	Q8_0	Comfortable
144 tok/s 87–231 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	16.8 GB	Q8_0	Comfortable
138 tok/s 83–221 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.8 GB	Q8_0	Comfortable
138 tok/s 83–221 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	16.8 GB	Q8_0	Comfortable
132 tok/s 79–211 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	16.8 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	16.8 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	16.8 GB	Q8_0	Comfortable
117 tok/s 70–188 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	16.8 GB	Q8_0	Comfortable
111 tok/s 67–178 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	16.8 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.9 GB	IQ4_XS	Tight
94.9 tok/s 57–152 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.8 GB	Q8_0	Comfortable
94.9 tok/s 57–152 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	16.8 GB	Q8_0	Comfortable
94.9 tok/s 57–152 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	16.8 GB	Q8_0	Comfortable
94.9 tok/s 57–152 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	16.8 GB	Q8_0	Comfortable
94.9 tok/s 57–152 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	16.8 GB	Q8_0	Comfortable
72.2 tok/s 43–116 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	16.8 GB	Q8_0	Comfortable
72.2 tok/s 43–116 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	16.8 GB	Q8_0	Comfortable
60.2 tok/s 36–96 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	16.8 GB	Q8_0	Comfortable
59.5 tok/s 36–95 · low confidence	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	9.8 GB	Q4_K_M	Tight
59.5 tok/s 36–95 · low confidence	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	9.8 GB	Q4_K_M	Tight
58.9 tok/s 35–94 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	16.8 GB	Q8_0	Comfortable
57.6 tok/s 35–92 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	16.8 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: Hugging Face,ServiceNow,NVIDIA,BigCode
Organisation type: Industry,Industry,Industry
Country: United States of America
Published: 29 February 2024
Authors: Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, Tianyang Liu, Max Tian, Denis Kocetkov, Arthur Zucker, Younes Belkada, Zijian Wang, Qian Liu, Dmitry Abulkhanov, Indraneil Paul, Zhuang Li, Wen-Ding Li, Megan Risdal, Jia Li, Jian Zhu, Terry Yue Zhuo, Evgenii Zheltonozhskii, Nii Osae Osae Dade, Wenhao Y…

What it does

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

Domain: Language
Task: Code generation, Code autocompletion

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: 15B
Training data: 913,230,000,000 tokens
Epochs: 4.49
Batch size: 4,100,000

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: 3.9 × 10²³ FLOP
How it was established: Reported

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.

Likely above 10²³ FLOP: Yes
Record confidence: Confident

Sources

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

Reference: StarCoder 2 and The Stack v2: The Next Generation
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run StarCoder 2 15B

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 StarCoder 2 15B

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

P102-101

Memory needed

8.9 GB

Fastest

226 tok/s

StarCoder 2 15B is small enough at 15B parameters that hardware is rarely the obstacle — 306 of the cards we track can run it, including cards several years old.

At the low end, a P102-101 handles it — 10 GB, at IQ4_XS, for about 18.9 tokens per second.

At the other end, a B200 generates roughly 226 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

StarCoder 2 15B was published by Hugging Face,ServiceNow,NVIDIA,BigCode, in United States of America, in February 2024. industry,Industry,Industry is the category the publisher falls under.

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

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

Understanding the speeds

The median result is around 21.1 tokens per second; 266 cards produce text faster than most people read it.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Training and provenance

Training it took roughly 3.9 × 10²³ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 913,230,000,000 tokens.

Step by step

How to choose a GPU for StarCoder 2 15B

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

Look at what StarCoder 2 15B actually needs — around 8.9 GB at IQ4_XS. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context StarCoder 2 15B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

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 StarCoder 2 15B by squeezing it further than you would want.
04

Sort by speed

Ranking by tokens per second for StarCoder 2 15B follows memory bandwidth, not core counts, which is why the B200 tops it at 226 tok/s.
05

Look at the headroom, not just the fit

Tight means StarCoder 2 15B loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
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 StarCoder 2 15B is settled.

Answers

StarCoder 2 15B — common questions

When was StarCoder 2 15B released?

StarCoder 2 15B was published in February 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.

What is StarCoder 2 15B used for?

StarCoder 2 15B works in Language, and is recorded as handling code generation, Code autocompletion. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download StarCoder 2 15B?

The weights for StarCoder 2 15B 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 StarCoder 2 15B?

Around 3.9 × 10²³ 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.

Can I run StarCoder 2 15B 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 StarCoder 2 15B is rarely worth using — the nearest miss we calculate is short by 2.6 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run StarCoder 2 15B faster?

Two cards buy memory rather than speed. That matters for StarCoder 2 15B only if one card cannot hold it — 306 can, so a second adds little.

Why does the quantisation differ between cards for StarCoder 2 15B?

A larger card holds a more accurate copy. Across the cards that run StarCoder 2 15B, 4 compression levels are used; the floor control above pins it to one.

How accurate are these StarCoder 2 15B speed estimates?

These are estimates with real error bars. The fastest result here, 136–361 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run StarCoder 2 15B?

The smallest card in our catalogue that holds StarCoder 2 15B is the P102-101, with 10 GB of memory. It runs the model at IQ4_XS using about 8.9 GB, and produces roughly 18.9 tokens per second. 306 cards in total can run it.

How fast is StarCoder 2 15B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 226 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 266 of the cards that can run StarCoder 2 15B clear that.

How much VRAM does StarCoder 2 15B need?

About 8.9 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 StarCoder 2 15B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q4_K_M, using about 9.8 GB and generating roughly 59.5 tokens per second — a tight fit.

Can I run StarCoder 2 15B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 13.3 GB and generating roughly 46.4 tokens per second — a tight fit.

Can I run StarCoder 2 15B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 16.8 GB and generating roughly 37.8 tokens per second — a comfortable fit.

Is StarCoder 2 15B open source?

Its weights are published, so StarCoder 2 15B 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 StarCoder 2 15B have?

StarCoder 2 15B has 15B parameters. 15B. 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 StarCoder 2 15B?

StarCoder 2 15B was published by Hugging Face,ServiceNow,NVIDIA,BigCode, based in United States of America, categorised as industry,Industry,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