DeepSeek-V4-Flash TPS calculator

Open weights DeepSeek 284B parameters April 2026

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 · 109 tok/s

Fastest card

B200

153 tok/s · 180 GB

Which GPUs can run DeepSeek-V4-Flash?

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
153 tok/s 92–245 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	153.0 GB	Q4_K_M	Tight
109 tok/s 66–175 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	119.9 GB	Q3_K_M	Tight
109 tok/s 66–175 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	119.9 GB	Q3_K_M	Tight
96.3 tok/s 58–154 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	219.1 GB	Q6_K	Tight
79.4 tok/s 48–127 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	153.0 GB	Q4_K_M	Tight
79.4 tok/s 48–127 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	153.0 GB	Q4_K_M	Tight
76.9 tok/s 46–123 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	219.1 GB	Q6_K	Tight
76.9 tok/s 46–123 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	219.1 GB	Q6_K	Tight
56.3 tok/s 34–90 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	219.1 GB	Q6_K	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: 24 April 2026

What it does

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

Domain: Language
Task: Language modeling/generation, Question answering

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: 284B
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: 2.5 × 10²⁴ FLOP

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 (unrestricted)

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: Discretionary
Record confidence: Likely

Sources

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

Reference: DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
Last updated: 8 June 2026

The extremes

The ten fastest GPUs that run DeepSeek-V4-Flash

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-V4-Flash

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

H200 NVL

Memory needed

119.9 GB

Fastest

153 tok/s

DeepSeek-V4-Flash reaches a parameter count of 284B. 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.

At the low end it is handled by H200 NVL, with a memory capacity of 141 GB, running it at a compression of Q3_K_M and producing around 109 tokens per second.

At the other end sits B200, generating roughly 153 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Where it came from

DeepSeek-V4-Flash was published by DeepSeek, in the country recorded as China, during April 2026. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering.

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

Across every card that can run it, the middle of the range sits at 79.4 tokens per second. Exceeding reading speed outright: 9 of them.

Mixture-of-experts routing is why the speeds here look high for the parameter count. Only a fraction is read per token, but the whole thing has to be loaded.

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.

What went into building it

The training run consumed about 2.5 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Its inclusion criterion: discretionary.

Step by step

How to choose a GPU for DeepSeek-V4-Flash

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

Start from what it actually needs, which is the requirement of DeepSeek-V4-Flash, needing around 119.9 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting DeepSeek-V4-Flash.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy, 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

Rank by throughput rather than spec sheet

The speed ordering is effectively an ordering by memory bandwidth, for DeepSeek-V4-Flash. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 153 tok/s.
05

Check the fit verdict before buying

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of DeepSeek-V4-Flash. 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

Following a card through to its own page shows every other model it can hold, which is the question that follows once you have settled on DeepSeek-V4-Flash.

Answers

DeepSeek-V4-Flash — common questions

DeepSeek-V4-Flash— 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.

DeepSeek-V4-Flash— how many parameters does it have?

It has a parameter count of 284B. 284B total, 13B active. 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-V4-Flash— who created it?

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

DeepSeek-V4-Flash— when was it released?

It was published in April 2026.

DeepSeek-V4-Flash— what is it used for?

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

DeepSeek-V4-Flash— 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.

DeepSeek-V4-Flash— how much compute was used to train it?

Training consumed around 2.5 × 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-V4-Flash— can I run it 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 model is rarely worth using. The nearest miss we calculate falls short by 37.8 GB. Every figure here assumes the whole model is resident on the card.

DeepSeek-V4-Flash— 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-V4-Flash— 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: 3. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

DeepSeek-V4-Flash— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 92–245 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-V4-Flash— 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 119.9 GB, and produces roughly 109 tokens per second. The number of cards able to run it in total: 9.

DeepSeek-V4-Flash— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 153 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-V4-Flash— how much VRAM does it need?

It needs about 119.9 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.

Source

Original publication

Record last updated 8 June 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