GLM-4.6 TPS calculator

Open weights Z.ai (Zhipu AI),Tsinghua University 357B parameters September 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

4 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI325X

256 GB · Q4_K_M · 12.8 tok/s

Fastest card

B300

17.0 tok/s · 288 GB

Which GPUs can run GLM-4.6?

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.

4 cards match

Calculating
Needs Quantisation Fit
17.0 tok/s

10–27 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 258.2 GB Q5_K_M Tight
13.5 tok/s

8–22 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 258.2 GB Q5_K_M Tight
13.5 tok/s

8–22 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 258.2 GB Q5_K_M Tight
12.8 tok/s

8–21 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 216.7 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),Tsinghua University
Organisation type
Industry,Academia
Country
China
Published
30 September 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, Question answering, Code generation, Quantitative reasoning, System control

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
357B

Similarly to GLM 4.5: 355 billion total parameters (reported) with 32 billion active parameters (assumed)

Training data
23,000,000,000,000 tokens

23T tokens (from Jaime's correspondence with the GLM team)

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

6 FLOP/parameter/token * 32000000000 active parameters [very likely assumption - everything else is reported to be same as at GLM 4.5] * 23000000000000 tokens = 4.42e24 FLOP

How it was established
Operation counting

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Wall-clock time
2,880 hours (120 days)

4 months (from Jaime's correspondence with the GLM team) 4 months * 30 days * 24 hours = 2880 hours

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

MIT license https://huggingface.co/zai-org/GLM-4.6

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

"We evaluated GLM-4.6 across eight public benchmarks covering agents, reasoning, and coding. Results show clear gains over GLM-4.5, with GLM-4.6 also holding competitive advantages over leading domestic and international models such as DeepSeek-V3.1-Terminus and Claude Sonnet 4."

Record confidence
Likely

Sources

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

Reference
GLM-4.6: Advanced Agentic, Reasoning and Coding Capabilities
Last updated
30 December 2025

The extremes

The ten fastest GPUs that run GLM-4.6

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.

  1. 01 B300 288 GB · 8,000 GB/s · Q5_K_M 17.0 tok/s
  2. 02 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q5_K_M 13.5 tok/s
  3. 03 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q5_K_M 13.5 tok/s
  4. 04 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q4_K_M 12.8 tok/s

What the numbers mean

What it takes to run this model

Minimum card

Radeon Instinct MI325X

Memory needed

216.7 GB

Fastest

17.0 tok/s

At 357B parameters, GLM-4.6 is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 4 of the cards we track can hold it on their own, and all of them are datacentre parts.

The smallest card that holds it is the Radeon Instinct MI325X with 256 GB, running it at Q4_K_M and producing around 12.8 tokens per second.

Top of the range is the B300, at roughly 17.0 tokens per second thanks to 8,000 GB/s of bandwidth.

What this model is

GLM-4.6 was published by Z.ai (Zhipu AI),Tsinghua University, in China, in September 2025. industry,Academia is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Question answering, Code generation, Quantitative reasoning, System control.

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.

What decides the speed

Across every card that can run it, the middle of the range is about 13.5 tokens per second, and 4 of them clear the ten tokens per second that roughly matches reading speed.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Training and provenance

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.

Around 23,000,000,000,000 tokens went into training it.

It is tracked in the underlying dataset for one reason in particular: discretionary.

Step by step

How to choose a GPU for GLM-4.6

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

  1. 01

    Read the memory figure first

    Look at what GLM-4.6 actually needs — around 216.7 GB at Q4_K_M. No amount of processing power compensates for a card that cannot hold it.

  2. 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 GLM-4.6.

  3. 03

    Choose how far you will compress it

    Compression is what makes GLM-4.6 fit smaller cards, at some cost in accuracy — Q4_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.

  4. 04

    Sort by speed

    Sort by speed to see how cards rank for GLM-4.6. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B300 tops it at 17.0 tok/s.

  5. 05

    Look at the headroom, not just the fit

    A tight fit runs GLM-4.6 but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.

  6. 06

    Check the card from the other side

    Following a card through to its own page shows every other model it can hold, which is the question that follows once GLM-4.6 is settled.

Answers

GLM-4.6 — common questions

01

Can I run GLM-4.6 if it does not fit in my GPU?

It can be split between the card and system memory, but GLM-4.6 generates painfully slowly that way — the nearest miss we calculate is short by 43.9 GB. Nothing on this page assumes offloading.

02

Would two GPUs run GLM-4.6 faster?

A second card roughly doubles the memory available but not the generation rate. With 4 cards already able to run GLM-4.6 alone, the case for pairing is weak.

03

Why does the quantisation differ between cards for GLM-4.6?

Each card is shown running the least-compressed copy it can hold, and GLM-4.6 appears at 2 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

04

How accurate are these GLM-4.6 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 10–27 tok/s on the B300 rather than a single number.

05

What GPU do I need to run GLM-4.6?

The smallest card in our catalogue that holds GLM-4.6 is the Radeon Instinct MI325X, with 256 GB of memory. It runs the model at Q4_K_M using about 216.7 GB, and produces roughly 12.8 tokens per second. 4 cards in total can run it.

06

How fast is GLM-4.6 on a GPU?

It depends on the card. The quickest we calculate is a B300 at about 17.0 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 4 of the cards that can run GLM-4.6 clear that.

07

How much VRAM does GLM-4.6 need?

About 216.7 GB at Q4_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.

08

Is GLM-4.6 open source?

Its weights are published, so GLM-4.6 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.

09

How many parameters does GLM-4.6 have?

GLM-4.6 has 357B parameters. Similarly to GLM 4.5: 355 billion total parameters (reported) with 32 billion active parameters (assumed). 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.

10

Who created GLM-4.6?

GLM-4.6 was published by Z.ai (Zhipu AI),Tsinghua University, based in China, categorised as industry,Academia.

11

When was GLM-4.6 released?

GLM-4.6 was published in September 2025.

12

What is GLM-4.6 used for?

GLM-4.6 works in Language, and is recorded as handling language modeling/generation, Question answering, Code generation, Quantitative reasoning, System control. 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.

13

Where can I download GLM-4.6?

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.

14

How much compute was used to train GLM-4.6?

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.

Source

Original publication

Record last updated 30 December 2025

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.