GLM-5 TPS calculator

Open weights Z.ai (Zhipu AI) 744B parameters February 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

0 cards that can run it

818 cards we hold specifications for

Which GPUs can run GLM-5?

Set the inputs, read the answer

A longer conversation needs more memory, which can push this model off smaller cards.

Hides cards that would only fit the model by compressing it below this point.

0 cards match

Calculating
Needs Quantisation Fit

No card in our catalogue can run this model with these settings.

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
Z.ai (Zhipu AI)
Organisation type
Industry
Country
China
Published
17 February 2026
Authors
Aohan Zeng, Xin Lv, Zhenyu Hou, Zhengxiao Du, Qinkai Zheng, Bin Chen, Da Yin, Chendi Ge, Chenghua Huang, Chengxing Xie, Chenzheng Zhu, Congfeng Yin, Cunxiang Wang, Gengzheng Pan, Hao Zeng, Haoke Zhang, Haoran Wang, Huilong Chen, Jiajie Zhang, Jian Jiao, Jiaqi Guo, Jingsen Wang, Jingzhao Du, Jinzhu Wu, Kedong Wang, Lei Li, Lin Fan, Lucen Zhong, Mingdao Liu, Mingming Zhao, Pengfan Du, Qian Dong, Rui…

What it does

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

Domain
Language
Task
Language modeling/generation

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
744B

"GLM-5 scales to 256 experts and reduces its layer count to 80 to minimize expert parallelism communication overhead. This results in a 744B parameter model"

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
6.8 × 10²⁴ FLOP

6 * 40B parameters * 28.5e12 tokens = 6.84e24 FLOP estimated

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
Huawei Ascend 910C

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)
Hugging Face
zai-org

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
GLM-5: from Vibe Coding to Agentic Engineering
Last updated
8 April 2026

What the numbers mean

What you need to run it

GLM-5 reaches a parameter count of 744B. 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: 0.

What this model is

GLM-5 was published by Z.ai (Zhipu AI), in the country recorded as China, during February 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.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. On Hugging Face it is published under the organisation zai-org.

How it was trained

The training run consumed about 6.8 × 10²⁴ FLOP, on hardware recorded as Huawei Ascend 910C. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The reason it appears in this catalogue at all: discretionary.

Step by step

How to choose a GPU for GLM-5

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

  1. 01

    Check what it needs before anything else

    The table lists every card able to hold GLM-5. That figure, not the headline performance of a card, is what decides whether it runs.

  2. 02

    Decide how long your conversations run

    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 GLM-5.

  3. 03

    Decide how much compression you will accept

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

  4. 04

    Compare tokens per second, not specifications

    The speed ordering is effectively an ordering by memory bandwidth, for GLM-5. It will not match a gaming ordering, because generation is bound by memory bandwidth.

  5. 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 GLM-5. 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.

  6. 06

    Check the card from the other side

    Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for GLM-5.

Answers

GLM-5 — common questions

01

GLM-5— 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: the range beneath each figure. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

02

GLM-5— 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.

03

GLM-5— how many parameters does it have?

It has a parameter count of 744B. "GLM-5 scales to 256 experts and reduces its layer count to 80 to minimize expert parallelism communication overhead. This results in a 744B parameter model". 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.

04

GLM-5— who created it?

It was published by Z.ai (Zhipu AI), based in China, an organisation categorised as industry.

05

GLM-5— when was it released?

It was published in February 2026.

06

GLM-5— what is it used for?

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

07

GLM-5— where can I download it?

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

08

GLM-5— how much compute was used to train it?

Training consumed around 6.8 × 10²⁴ FLOP, on hardware recorded as Huawei Ascend 910C. 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.

09

GLM-5— 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 191.6 GB. Every figure here assumes the whole model is resident on the card.

10

GLM-5— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 0. So a second card is rarely the answer here.

11

GLM-5— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Source

Original publication

Record last updated 8 April 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.