GLM-4.5-Air TPS calculator

Open weights Z.ai (Zhipu AI),Tsinghua University 106B parameters August 2025

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

43 of 818 cards that can run it

Smallest card that fits

Radeon Instinct MI200

64 GB · IQ4_XS · 69.7 tok/s

Fastest card

B200

178 tok/s · 180 GB

Which GPUs can run GLM-4.5-Air?

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

43 cards match

Calculating

					Needs	Quantisation	Fit
178 tok/s 107–284 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	108.8 GB	Q8_0	Comfortable
178 tok/s 107–284 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	108.8 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	108.8 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	108.8 GB	Q8_0	Comfortable
133 tok/s 80–213 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	71.8 GB	Q5_K_M	Tight
133 tok/s 80–213 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	71.8 GB	Q5_K_M	Tight
127 tok/s 76–203 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	84.1 GB	Q6_K	Tight
113 tok/s 68–181 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	108.8 GB	Q8_0	Tight
110 tok/s 66–176 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	53.3 GB	IQ4_XS	Tight
109 tok/s 65–174 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	108.8 GB	Q8_0	Tight
109 tok/s 65–174 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	108.8 GB	Q8_0	Tight
108 tok/s 65–173 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	84.1 GB	Q6_K	Tight
108 tok/s 65–173 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	84.1 GB	Q6_K	Tight
108 tok/s 65–173 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	84.1 GB	Q6_K	Tight
104 tok/s 62–166 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	108.8 GB	Q8_0	Comfortable
92.2 tok/s 55–148 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	108.8 GB	Q8_0	Tight
92.2 tok/s 55–148 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	108.8 GB	Q8_0	Comfortable
92.2 tok/s 55–148 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	108.8 GB	Q8_0	Comfortable
80.9 tok/s 49–129 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	71.8 GB	Q5_K_M	Tight
80.9 tok/s 49–129 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	71.8 GB	Q5_K_M	Tight
80.9 tok/s 49–129 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	71.8 GB	Q5_K_M	Tight
80.9 tok/s 49–129 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	71.8 GB	Q5_K_M	Tight
80.9 tok/s 49–129 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	71.8 GB	Q5_K_M	Tight
80.9 tok/s 49–129 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	71.8 GB	Q5_K_M	Tight
76.9 tok/s 46–123 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	71.8 GB	Q5_K_M	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: Z.ai (Zhipu AI),Tsinghua University
Organisation type: Industry,Academia
Country: China
Published: 5 August 2025
Authors: Bin Chen, Chengxing Xie, Cunxiang Wang, Da Yin, Hao Zeng, Jiajie Zhang, Kedong Wang, Lucen Zhong, Mingdao Liu, Rui Lu, Shulin Cao, Xiaohan Zhang, Xuancheng Huang, Yao Wei, Yean Cheng, Yifan An, Yilin Niu, Yuanhao Wen, Yushi Bai, Zhengxiao Du, Zihan Wang (汪子涵), Zilin Zhu

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, Visual question answering, Image captioning, Video description, Table tasks, Character recognition (OCR)

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: 106B
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: 1.7 × 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)
Training code: Unreleased
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.

Record confidence: Confident

Sources

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

Reference: GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Last updated: 9 February 2026

The extremes

The ten fastest GPUs for GLM-4.5-Air

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 GLM-4.5-Air

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

Hardware requirements in practice

Minimum card

Radeon Instinct MI200

Memory needed

53.3 GB

Fastest

178 tok/s

GLM-4.5-Air sits at 106B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 43 of the cards we track can hold it.

The entry point is the Radeon Instinct MI200: 64 GB of memory, IQ4_XS compression, roughly 69.7 tokens per second.

Top of the range is the B200, at roughly 178 tokens per second thanks to 8,000 GB/s of bandwidth.

About this model

GLM-4.5-Air was published by Z.ai (Zhipu AI),Tsinghua University, in China, in August 2025. It comes out of industry,Academia.

It works in Language, and is recorded as doing language modeling/generation, Question answering, Visual question answering, Image captioning, Video description, Table tasks, Character recognition (OCR).

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the zai-org organisation on Hugging Face.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 80.9 tokens per second, and 41 of them clear the ten tokens per second that roughly matches reading speed.

Because it routes each token through a subset of its weights, it produces text at the pace of a much smaller model. The catch is memory: all of it still has to fit, so the speed is a bonus rather than a discount on hardware.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

Training and provenance

Producing it required around 1.7 × 10²⁴ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Step by step

How to choose a GPU for GLM-4.5-Air

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

The table lists every card that can hold GLM-4.5-Air — around 53.3 GB at IQ4_XS. That figure, not the card's headline performance, is what decides whether it runs.
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 GLM-4.5-Air stops fitting a card that seemed fine.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold — IQ4_XS on the smallest card that fits. Setting a floor drops the cards that only manage GLM-4.5-Air by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for GLM-4.5-Air follows memory bandwidth, not core counts, which is why the B200 tops it at 178 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage GLM-4.5-Air from those with room to spare. Buy for the second if the context might grow.
06

Open the card you have settled on

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond GLM-4.5-Air.

Answers

GLM-4.5-Air — common questions

How much compute was used to train GLM-4.5-Air?

Around 1.7 × 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 GLM-4.5-Air 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 GLM-4.5-Air is rarely worth using — the nearest miss we calculate is short by 16.3 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run GLM-4.5-Air faster?

Two cards buy memory rather than speed. That matters for GLM-4.5-Air only if one card cannot hold it — 43 can, so a second adds little.

Why does the quantisation differ between cards for GLM-4.5-Air?

Because capacity varies, so does how hard GLM-4.5-Air has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these GLM-4.5-Air speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 107–284 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run GLM-4.5-Air?

The smallest card in our catalogue that holds GLM-4.5-Air is the Radeon Instinct MI200, with 64 GB of memory. It runs the model at IQ4_XS using about 53.3 GB, and produces roughly 69.7 tokens per second. 43 cards in total can run it.

How fast is GLM-4.5-Air on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 178 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 41 of the cards that can run GLM-4.5-Air clear that.

How much VRAM does GLM-4.5-Air need?

About 53.3 GB at IQ4_XS 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 GLM-4.5-Air open source?

Its weights are published, so GLM-4.5-Air 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.

How many parameters does GLM-4.5-Air have?

GLM-4.5-Air has 106B parameters. 106B parameters, 12B 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.

Who created GLM-4.5-Air?

GLM-4.5-Air was published by Z.ai (Zhipu AI),Tsinghua University, based in China, categorised as industry,Academia.

When was GLM-4.5-Air released?

GLM-4.5-Air was published in August 2025.

What is GLM-4.5-Air used for?

GLM-4.5-Air works in Language, and is recorded as handling language modeling/generation, Question answering, Visual question answering, Image captioning, Video description, Table tasks, Character recognition (OCR). These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download GLM-4.5-Air?

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

Source

Original publication

Record last updated 9 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