PengCheng Mind (鹏城脑海) TPS calculator

Open weights Peng Cheng Laboratory 200B parameters September 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

17 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI250

128 GB · IQ4_XS · 13.3 tok/s

Fastest card

B200

30.3 tok/s · 180 GB

Which GPUs can run PengCheng Mind (鹏城脑海)?

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

17 cards match

Calculating

					Needs	Quantisation	Fit
30.3 tok/s 18–48 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	145.0 GB	Q5_K_M	Tight
26.6 tok/s 16–43 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	110.1 GB	IQ4_XS	Tight
23.9 tok/s 14–38 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	121.7 GB	Q4_K_M	Tight
23.9 tok/s 14–38 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	121.7 GB	Q4_K_M	Tight
21.6 tok/s 13–35 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	110.1 GB	IQ4_XS	Tight
16.9 tok/s 10–27 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	214.8 GB	Q8_0	Comfortable
13.5 tok/s 8–22 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	214.8 GB	Q8_0	Comfortable
13.5 tok/s 8–22 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	214.8 GB	Q8_0	Comfortable
13.3 tok/s 8–21 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	110.1 GB	IQ4_XS	Tight
13.3 tok/s 8–21 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	110.1 GB	IQ4_XS	Tight
12.8 tok/s 8–20 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	168.3 GB	Q6_K	Tight
12.8 tok/s 8–20 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	168.3 GB	Q6_K	Tight
11.1 tok/s 7–18 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	110.1 GB	IQ4_XS	Tight
10.9 tok/s 7–17 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	110.1 GB	IQ4_XS	Tight
9.9 tok/s 6–16 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	214.8 GB	Q8_0	Tight
1.4 tok/s 1–2 · low confidence	GB10 NVIDIA	128 GB	273 GB/s	Oct 2025	110.1 GB	IQ4_XS	Tight
1.4 tok/s 1–2 · low confidence	Jetson T5000 NVIDIA	128 GB	273 GB/s	Aug 2025	110.1 GB	IQ4_XS	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: Peng Cheng Laboratory
Organisation type: Academia
Country: China
Published: 21 September 2023

What it does

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

Domain: Language
Task: Chat, Code generation, Translation

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: 200B
Training data: tokens

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: Ascend (昇腾) 910
Chips used: 144
Data centre: PengCheng Cloud Brain II

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)

How it is classified

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

Record confidence: Confident

Sources

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

Reference: OpenI启智社区/PengCheng.Mind
Last updated: 11 February 2026

The extremes

The ten fastest GPUs that run PengCheng Mind (鹏城脑海)

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 PengCheng Mind (鹏城脑海)

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

Radeon Instinct MI250

Memory needed

110.1 GB

Fastest

30.3 tok/s

PengCheng Mind (鹏城脑海) reaches a parameter count of 200B. 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: 17.

The least hardware that works is Radeon Instinct MI250, with a memory capacity of 128 GB, running it at a compression of IQ4_XS and producing around 13.3 tokens per second.

At the other end sits B200, generating roughly 30.3 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

PengCheng Mind (鹏城脑海) was published by Peng Cheng Laboratory, in the country recorded as China, during September 2023. It comes out of an organisation categorised as academia.

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

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

What decides the speed

The median result is around 13.3 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 14 of them.

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.

Step by step

How to choose a GPU for PengCheng Mind (鹏城脑海)

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

The table lists every card able to hold PengCheng Mind (鹏城脑海), needing around 110.1 GB at a compression of IQ4_XS. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for PengCheng Mind (鹏城脑海).
03

Set a quality floor

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of IQ4_XS 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

Ranking by tokens per second follows memory bandwidth rather than core counts, for PengCheng Mind (鹏城脑海). It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 30.3 tok/s.
05

Look at the headroom, not just the fit

Tight means it loads and works with no room to raise the context later, in the case of PengCheng Mind (鹏城脑海). 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

See what else that card runs

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 PengCheng Mind (鹏城脑海).

Answers

PengCheng Mind (鹏城脑海) — common questions

PengCheng Mind (鹏城脑海)— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 18–48 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

PengCheng Mind (鹏城脑海)— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI250, with a memory capacity of 128 GB. It runs the model at a compression of IQ4_XS using about 110.1 GB, and produces roughly 13.3 tokens per second. The number of cards able to run it in total: 17.

PengCheng Mind (鹏城脑海)— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 30.3 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: 14.

PengCheng Mind (鹏城脑海)— how much VRAM does it need?

It needs about 110.1 GB at a compression of IQ4_XS, 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.

PengCheng Mind (鹏城脑海)— 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.

PengCheng Mind (鹏城脑海)— how many parameters does it have?

It has a parameter count of 200B. "PengCheng.Mind 又称鹏城·脑海是鹏城实验室开发、开源、开放的基于Transformer架构的自回归式语言模型，目前包含7B、200B两个版本". 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.

PengCheng Mind (鹏城脑海)— who created it?

It was published by Peng Cheng Laboratory, based in China, an organisation categorised as academia.

PengCheng Mind (鹏城脑海)— when was it released?

It was published in September 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.

PengCheng Mind (鹏城脑海)— what is it used for?

It works in the domain of Language, and is recorded as handling the task of chat, Code generation, Translation. 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.

PengCheng Mind (鹏城脑海)— 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.

PengCheng Mind (鹏城脑海)— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 35.3 GB. Every figure here assumes the whole model is resident on the card.

PengCheng Mind (鹏城脑海)— 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: 17. So a second card is rarely the answer here.

PengCheng Mind (鹏城脑海)— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Source

Original publication

Record last updated 11 February 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