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 cards that can run it

818 cards we hold specifications for

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 that run 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

DeepSeek-Coder-V2 236B reaches a parameter count of 236B. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 9.

The least hardware that works is H200 NVL, with a memory capacity of 141 GB, running it at a compression of Q3_K_M and producing around 23.7 tokens per second.

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

Where it came from

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

It works in the domain of Language, and is recorded as performing the task of code generation, Code autocompletion.

Rather than being trained from scratch, it is derived from DeepSeek-V2 (MoE-236B). 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. On Hugging Face it is published under the organisation deepseek-ai.

Understanding the speeds

Across every card that can run it, the middle of the range sits at 13.3 tokens per second. Producing text faster than most people read it: 9 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.

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 arithmetic totalling around 1.3 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

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

Its inclusion criterion: 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, needing around 116.0 GB at a compression of Q3_K_M. 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, because at long context a card that handles short questions easily can be dropped by DeepSeek-Coder-V2 236B.
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

Ranking by tokens per second follows memory bandwidth rather than core counts, for DeepSeek-Coder-V2 236B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 33.2 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 DeepSeek-Coder-V2 236B. 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

Check the card from the other side

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

Answers

DeepSeek-Coder-V2 236B — common questions

DeepSeek-Coder-V2 236B— how many parameters does it have?

It has a parameter count of 236B. 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.

DeepSeek-Coder-V2 236B— who created it?

It was published by DeepSeek, based in China, an organisation categorised as industry.

DeepSeek-Coder-V2 236B— when was it released?

It 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.

DeepSeek-Coder-V2 236B— what is it used for?

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

DeepSeek-Coder-V2 236B— where can I download it?

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

DeepSeek-Coder-V2 236B— how much compute was used to train it?

Training consumed 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.

DeepSeek-Coder-V2 236B— 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 28.3 GB. Every figure here assumes the whole model is resident on the card.

DeepSeek-Coder-V2 236B— 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: 9. So a second card is rarely the answer here.

DeepSeek-Coder-V2 236B— 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: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

DeepSeek-Coder-V2 236B— 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: 20–53 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

DeepSeek-Coder-V2 236B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is H200 NVL, with a memory capacity of 141 GB. It runs the model at a compression of Q3_K_M using about 116.0 GB, and produces roughly 23.7 tokens per second. The number of cards able to run it in total: 9.

DeepSeek-Coder-V2 236B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is 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 the number of cards clearing that: 9.

DeepSeek-Coder-V2 236B— how much VRAM does it need?

It needs about 116.0 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.

DeepSeek-Coder-V2 236B— 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.

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