GLM-4.7 TPS calculator
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
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
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.
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
mixture of experts (MoE) with 358B total, 32B active
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
Training tokens not disclosed. Presuming this is a post-training update from GLM-4.5 (23T tokens) with minor additional compute, training compute is at least: 6 FLOP/parameter/token * 32B active parameters * 23T tokens = 4.42e24 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
MIT license
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
near-frontier for open models and models from Chinese developers
Sources
Where this record came from and when it was last checked.
- Last updated
- 29 January 2026
The extremes
The ten fastest GPUs for 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.
- 01 B200 180 GB · 8,000 GB/s · Q3_K_M 142 tok/s
- 02 B300 288 GB · 8,000 GB/s · Q5_K_M 93.9 tok/s
- 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q5_K_M 75.0 tok/s
- 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q5_K_M 75.0 tok/s
- 05 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q3_K_M 73.7 tok/s
- 06 Radeon Instinct MI308X 192 GB · 5,325 GB/s · Q3_K_M 73.7 tok/s
- 07 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q4_K_M 71.0 tok/s
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.
- 01 B200 180 GB · needs 155.2 GB · Q3_K_M · tight 142 tok/s
- 02 Radeon Instinct MI300X 192 GB · needs 155.2 GB · Q3_K_M · tight 73.7 tok/s
- 03 Radeon Instinct MI308X 192 GB · needs 155.2 GB · Q3_K_M · tight 73.7 tok/s
- 04 Radeon Instinct MI325X 256 GB · needs 196.8 GB · Q4_K_M · tight 71.0 tok/s
- 05 B300 288 GB · needs 238.5 GB · Q5_K_M · tight 93.9 tok/s
- 06 Radeon Instinct MI350X 288 GB · needs 238.5 GB · Q5_K_M · tight 75.0 tok/s
- 07 Radeon Instinct MI355X 288 GB · needs 238.5 GB · Q5_K_M · tight 75.0 tok/s
What the numbers mean
What you need to run it
Minimum card
B200
Memory needed
155.2 GB
Fastest
142 tok/s
At 358B parameters, GLM-4.7 is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 7 of the cards we track can hold it on their own, and all of them are datacentre parts.
The least hardware that works is a B200. Its 180 GB is enough at Q3_K_M compression, giving roughly 142 tokens per second.
Top of the range is the B200, at roughly 142 tokens per second thanks to 8,000 GB/s of bandwidth.
Background
GLM-4.7 was published by Z.ai (Zhipu AI), in China, in December 2025. It comes out of industry.
It works in Language, and is recorded as doing language modeling/generation, Code generation.
Its starting point was GLM-4.5 — most models at this scale are adapted from an existing base rather than built from nothing.
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.
Reading the throughput figures
Half the cards that hold it manage more than 75.0 tokens per second, and 7 exceed reading speed outright.
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 describes the cost of creating it and has no bearing on how quickly it generates text.
Its inclusion criterion is 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 — around 155.2 GB at 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 GLM-4.7 fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
-
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 — generation is bound by memory bandwidth, which is why the B200 tops it at 142 tok/s.
-
05
Check the fit verdict before buying
The fit column separates cards that just manage GLM-4.7 from those with room to spare. Buy for the second if the context might grow.
-
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. Worth a look before buying for GLM-4.7 alone — a card is usually bought for more than one model.
Answers
GLM-4.7 — common questions
Is GLM-4.7 open source?
Its weights are published, so GLM-4.7 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-4.7 have?
GLM-4.7 has 358B parameters. 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.
Who created GLM-4.7?
GLM-4.7 was published by Z.ai (Zhipu AI), based in China, categorised as industry.
When was GLM-4.7 released?
GLM-4.7 was published in December 2025.
What is GLM-4.7 used for?
GLM-4.7 works in Language, and is recorded as handling language modeling/generation, Code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Where can I download GLM-4.7?
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.
How much compute was used to train GLM-4.7?
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.
Can I run GLM-4.7 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-4.7 is rarely worth using — the nearest miss we calculate is short by 69.9 GB. Every figure here assumes the whole model is on the card.
Would two GPUs run GLM-4.7 faster?
Capacity adds across cards; throughput does not. Since 7 of the cards we track already hold GLM-4.7 on their own, a second card is rarely the answer here.
Why does the quantisation differ between cards for GLM-4.7?
A larger card holds a more accurate copy. Across the cards that run GLM-4.7, 3 compression levels are used; the floor control above pins it to one.
How accurate are these GLM-4.7 speed estimates?
Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 85–227 tok/s on the B200 rather than a single number.
What GPU do I need to run GLM-4.7?
The smallest card in our catalogue that holds GLM-4.7 is the B200, with 180 GB of memory. It runs the model at Q3_K_M using about 155.2 GB, and produces roughly 142 tokens per second. 7 cards in total can run it.
How fast is GLM-4.7 on a GPU?
It depends on the card. The quickest we calculate is a 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 7 of the cards that can run GLM-4.7 clear that.
How much VRAM does GLM-4.7 need?
About 155.2 GB at Q3_K_M 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.
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.