DeepSeek-Coder-V2 236B TPS calculator

Open weights DeepSeek 236B parameters June 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

9 of 818 cards that can run it

Smallest card that fits

H200 NVL

141 GB · Q3_K_M · 23.7 tok/s

Fastest card

B200

33.2 tok/s · 180 GB

Which GPUs can run DeepSeek-Coder-V2 236B?

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

9 cards match

Calculating

					Needs	Quantisation	Fit
33.2 tok/s 20–53 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	143.5 GB	Q4_K_M	Tight
23.7 tok/s 14–38 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	116.0 GB	Q3_K_M	Tight
23.7 tok/s 14–38 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	116.0 GB	Q3_K_M	Tight
14.4 tok/s 9–23 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	253.4 GB	Q8_0	Tight
13.3 tok/s 8–21 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	171.0 GB	Q5_K_M	Tight
13.3 tok/s 8–21 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	171.0 GB	Q5_K_M	Tight
12.2 tok/s 7–20 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	198.4 GB	Q6_K	Tight
11.5 tok/s 7–18 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	253.4 GB	Q8_0	Tight
11.5 tok/s 7–18 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	253.4 GB	Q8_0	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: DeepSeek
Organisation type: Industry
Country: China
Published: 17 June 2024
Authors: Qihao Zhu, Daya Guo, Zhihong Shao, Dejian Yang, Peiyi Wang, Runxin Xu, Y. Wu, Yukun Li, Huazuo Gao, Shirong Ma, Wangding Zeng, Xiao Bi, Zihui Gu, Hanwei Xu, Damai Dai, Kai Dong, Liyue Zhang, Yishi Piao, Zhibin Gou, Zhenda Xie, Zhewen Hao, Bingxuan Wang, Junxiao Song, Deli Chen, Xin Xie, Kang Guan, Yuxiang You, Aixin Liu, Qiushi Du, Wenjun Gao, Xuan Lu, Qinyu Chen, Yaohui Wang, Chengqi Deng, Jiashi…

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
Approach: Self-supervised learning
Base model: DeepSeek-V2 (MoE-236B)

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: 236B
Training data: 3,191,000,000,000 tokens
Batch size: 36,864,000

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: 1.3 × 10²⁴ FLOP
How it was established: Operation counting

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Data centre: The paper does not mention any hardware, GPUs or any information regarding the hardware used.

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
Hugging Face: deepseek-ai

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
Why it is tracked: SOTA improvement
Record confidence: Confident

Sources

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

Reference: DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
Last updated: 28 November 2025

The extremes

The ten fastest GPUs for DeepSeek-Coder-V2 236B

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 DeepSeek-Coder-V2 236B

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

H200 NVL

Memory needed

116.0 GB

Fastest

33.2 tok/s

At 236B parameters, DeepSeek-Coder-V2 236B is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 9 of the cards we track can hold it on their own, and all of them are datacentre parts.

The least hardware that works is a H200 NVL. Its 141 GB is enough at Q3_K_M compression, giving roughly 23.7 tokens per second.

At the other end, a B200 generates roughly 33.2 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

DeepSeek-Coder-V2 236B was published by DeepSeek, in China, in June 2024. industry is the category the publisher falls under.

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

It is derived from DeepSeek-V2 (MoE-236B) rather than trained from scratch, which is the usual way a specialised model is produced.

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. It is published under the deepseek-ai organisation on Hugging Face.

Understanding the speeds

Across every card that can run it, the middle of the range is about 13.3 tokens per second, and 9 of them clear the ten tokens per second that roughly matches reading speed.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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.

How it was trained

Producing it required around 1.3 × 10²⁴ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

It was trained on about 3,191,000,000,000 tokens of text.

Its inclusion criterion is sOTA improvement.

Step by step

How to choose a GPU for DeepSeek-Coder-V2 236B

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

Every card here has been checked against DeepSeek-Coder-V2 236B — around 116.0 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
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 DeepSeek-Coder-V2 236B can slip off a card that handles short questions easily.
03

Set a quality floor

Compression is what makes DeepSeek-Coder-V2 236B fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Compare tokens per second, not specifications

Ranking by tokens per second for DeepSeek-Coder-V2 236B follows memory bandwidth, not core counts, which is why the B200 tops it at 33.2 tok/s.
05

Check the fit verdict before buying

Tight means DeepSeek-Coder-V2 236B 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

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond DeepSeek-Coder-V2 236B.

Answers

DeepSeek-Coder-V2 236B — common questions

How many parameters does DeepSeek-Coder-V2 236B have?

DeepSeek-Coder-V2 236B has 236B parameters. Mixture of experts model. 21B parameters activated per token. 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 DeepSeek-Coder-V2 236B?

DeepSeek-Coder-V2 236B was published by DeepSeek, based in China, categorised as industry.

When was DeepSeek-Coder-V2 236B released?

DeepSeek-Coder-V2 236B was published in June 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 DeepSeek-Coder-V2 236B used for?

DeepSeek-Coder-V2 236B works in Language, and is recorded as handling code generation, Code autocompletion. 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.

Where can I download DeepSeek-Coder-V2 236B?

Its weights are published under the deepseek-ai organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

How much compute was used to train DeepSeek-Coder-V2 236B?

Around 1.3 × 10²⁴ 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 DeepSeek-Coder-V2 236B if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down — the nearest miss we calculate is short by 28.3 GB. Our figures for DeepSeek-Coder-V2 236B assume it is fully resident.

Would two GPUs run DeepSeek-Coder-V2 236B faster?

A second card roughly doubles the memory available but not the generation rate. With 9 cards already able to run DeepSeek-Coder-V2 236B alone, the case for pairing is weak.

Why does the quantisation differ between cards for DeepSeek-Coder-V2 236B?

Each card is shown running the least-compressed copy it can hold, and DeepSeek-Coder-V2 236B appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these DeepSeek-Coder-V2 236B speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 20–53 tok/s on the B200 rather than a single number.

What GPU do I need to run DeepSeek-Coder-V2 236B?

The smallest card in our catalogue that holds DeepSeek-Coder-V2 236B is the H200 NVL, with 141 GB of memory. It runs the model at Q3_K_M using about 116.0 GB, and produces roughly 23.7 tokens per second. 9 cards in total can run it.

How fast is DeepSeek-Coder-V2 236B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 33.2 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 9 of the cards that can run DeepSeek-Coder-V2 236B clear that.

How much VRAM does DeepSeek-Coder-V2 236B need?

About 116.0 GB at Q3_K_M 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.

Is DeepSeek-Coder-V2 236B open source?

Its weights are published, so DeepSeek-Coder-V2 236B 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.

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