GLM-4.7 TPS calculator

Open weights Z.ai (Zhipu AI) 358B parameters December 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

7 cards that can run it

818 cards we hold specifications for

Smallest card that fits

B200

180 GB · Q3_K_M · 142 tok/s

Fastest card

B200

142 tok/s · 180 GB

Which GPUs can run GLM-4.7?

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

7 cards match

Calculating

					Needs	Quantisation	Fit
142 tok/s 85–227 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	155.2 GB	Q3_K_M	Tight
93.9 tok/s 56–150 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	238.5 GB	Q5_K_M	Tight
75.0 tok/s 45–120 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	238.5 GB	Q5_K_M	Tight
75.0 tok/s 45–120 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	238.5 GB	Q5_K_M	Tight
73.7 tok/s 44–118 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	155.2 GB	Q3_K_M	Tight
73.7 tok/s 44–118 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	155.2 GB	Q3_K_M	Tight
71.0 tok/s 43–114 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	196.8 GB	Q4_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)
Organisation type: Industry
Country: China
Published: 22 December 2025

What it does

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

Domain: Language
Task: Language modeling/generation, Code generation
Base model: GLM-4.5

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: 358B
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: 4.4 × 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.

Why it is tracked: Discretionary
Record confidence: Likely

Sources

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

Last updated: 29 January 2026

The extremes

The ten fastest GPUs that run GLM-4.7

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-4.7

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

B200

Memory needed

155.2 GB

Fastest

142 tok/s

GLM-4.7 reaches a parameter count of 358B. 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: 7.

The least hardware that works is B200, with a memory capacity of 180 GB, running it at a compression of Q3_K_M and producing around 142 tokens per second.

Top of the range is B200, generating roughly 142 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

GLM-4.7 was published by Z.ai (Zhipu AI), in the country recorded as China, during December 2025. It comes out of an organisation categorised as industry.

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

Its starting point was an existing base model, GLM-4.5. That is why it shares the base model's general shape and size.

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. On Hugging Face it is published under the organisation zai-org.

Reading the throughput figures

Half the cards that hold it manage more than 75.0 tokens per second. Exceeding reading speed outright: 7 of them.

This is a mixture-of-experts model, which routes each token through only part of itself. It therefore generates far faster than its total size suggests — while still needing every parameter resident in memory, so it is quick without being cheap to hold.

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.

How it was trained

The training run consumed about 4.4 × 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 GLM-4.7

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

Every card here has been checked against GLM-4.7, needing around 155.2 GB at a compression of Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for GLM-4.7.
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

Sort by speed to see how cards rank for GLM-4.7. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 142 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage it from those with room to spare, in the case of GLM-4.7. 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

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-4.7.

Answers

GLM-4.7 — common questions

GLM-4.7— 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.

GLM-4.7— how many parameters does it have?

It has a parameter count of 358B. mixture of experts (MoE) with 358B total, 32B 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.

GLM-4.7— who created it?

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

GLM-4.7— when was it released?

It was published in December 2025.

GLM-4.7— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

GLM-4.7— 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.

GLM-4.7— how much compute was used to train it?

Training consumed around 4.4 × 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.

GLM-4.7— 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 69.9 GB. Every figure here assumes the whole model is resident on the card.

GLM-4.7— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 7. So a second card is rarely the answer here.

GLM-4.7— 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: 3. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

GLM-4.7— 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: 85–227 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

GLM-4.7— what GPU do I need to run it?

The smallest card in our catalogue that holds it is B200, with a memory capacity of 180 GB. It runs the model at a compression of Q3_K_M using about 155.2 GB, and produces roughly 142 tokens per second. The number of cards able to run it in total: 7.

GLM-4.7— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 142 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: 7.

GLM-4.7— how much VRAM does it need?

It needs about 155.2 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 29 January 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