GLM-10B-unidirectional TPS calculator

Open weights Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI,Massachusetts Institute of Technology (MIT) 10B parameters March 2021

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

509 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 5110P

8 GB · Q4_K_M · 20.3 tok/s

Fastest card

B200

339 tok/s · 180 GB

Which GPUs can run GLM-10B-unidirectional?

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

509 cards match

Calculating

					Needs	Quantisation	Fit
339 tok/s 203–542 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	11.4 GB	Q8_0	Comfortable
339 tok/s 203–542 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	11.4 GB	Q8_0	Comfortable
271 tok/s 162–433 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	11.4 GB	Q8_0	Comfortable
271 tok/s 162–433 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	11.4 GB	Q8_0	Comfortable
216 tok/s 130–346 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	11.4 GB	Q8_0	Comfortable
207 tok/s 124–331 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	11.4 GB	Q8_0	Comfortable
207 tok/s 124–331 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	11.4 GB	Q8_0	Comfortable
198 tok/s 119–317 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	11.4 GB	Q8_0	Comfortable
176 tok/s 106–281 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	11.4 GB	Q8_0	Comfortable
176 tok/s 106–281 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	11.4 GB	Q8_0	Comfortable
176 tok/s 106–281 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	11.4 GB	Q8_0	Comfortable
167 tok/s 100–267 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	11.4 GB	Q8_0	Comfortable
146 tok/s 87–233 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.7 GB	Q4_K_M	Tight
142 tok/s 85–228 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	11.4 GB	Q8_0	Comfortable
142 tok/s 85–228 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	11.4 GB	Q8_0	Comfortable
142 tok/s 85–228 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	11.4 GB	Q8_0	Comfortable
142 tok/s 85–228 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	11.4 GB	Q8_0	Comfortable
142 tok/s 85–228 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	11.4 GB	Q8_0	Comfortable
118 tok/s 71–189 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	7.9 GB	Q5_K_M	Tight
108 tok/s 65–173 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	11.4 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	11.4 GB	Q8_0	Comfortable
90.3 tok/s 54–144 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	11.4 GB	Q8_0	Comfortable
88.4 tok/s 53–141 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	11.4 GB	Q8_0	Comfortable
86.4 tok/s 52–138 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	11.4 GB	Q8_0	Comfortable
86.4 tok/s 52–138 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	11.4 GB	Q8_0	Comfortable

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: Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI,Massachusetts Institute of Technology (MIT)
Organisation type: Academia,Academia,Academia
Country: China, United States of America
Published: 18 March 2021
Authors: Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, Jie Tang

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: 10B
Training data: tokens
Epochs: 1

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: Open source

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence: Confident
Citations: 1,919
Benchmark data: GLM-10B-unidirectional

Sources

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

Reference: GLM: General Language Model Pretraining with Autoregressive Blank Infilling
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run GLM-10B-unidirectional

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-10B-unidirectional

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 it takes to run this model

Minimum card

Xeon Phi 5110P

Memory needed

6.7 GB

Fastest

339 tok/s

GLM-10B-unidirectional reaches a parameter count of 10B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 509.

The smallest card that holds it is Xeon Phi 5110P, with a memory capacity of 8 GB, running it at a compression of Q4_K_M and producing around 20.3 tokens per second.

Top of the range is B200, generating roughly 339 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

GLM-10B-unidirectional was published by Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI,Massachusetts Institute of Technology (MIT), in the country recorded as China, during March 2021. It comes out of an organisation categorised as academia,Academia,Academia.

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

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.

How fast it runs, and why

Across every card that can run it, the middle of the range sits at 22.0 tokens per second. Producing text faster than most people read it: 469 of them.

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

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.

Step by step

How to choose a GPU for GLM-10B-unidirectional

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

01

Start from the memory column

The table lists every card able to hold GLM-10B-unidirectional, needing around 6.7 GB at a compression of Q4_K_M. No amount of processing power compensates for a card that cannot hold it.
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-10B-unidirectional.
03

Set a quality floor

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q4_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-10B-unidirectional. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 339 tok/s.
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-10B-unidirectional. 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

See what else that card runs

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-10B-unidirectional.

Answers

GLM-10B-unidirectional — common questions

GLM-10B-unidirectional— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q8_0, using about 11.4 GB and generating roughly 47.9 tokens per second. The fit is comfortable.

GLM-10B-unidirectional— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q8_0, using about 11.4 GB and generating roughly 56.8 tokens per second. The fit is comfortable.

GLM-10B-unidirectional— 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-10B-unidirectional— how many parameters does it have?

It has a parameter count of 10B. 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-10B-unidirectional— who created it?

It was published by Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI,Massachusetts Institute of Technology (MIT), based in China, an organisation categorised as academia,Academia,Academia.

GLM-10B-unidirectional— when was it released?

It was published in March 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

GLM-10B-unidirectional— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

GLM-10B-unidirectional— where can I download it?

The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

GLM-10B-unidirectional— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 1.3 GB. Every figure here assumes the whole model is resident on the card.

GLM-10B-unidirectional— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 509. So a second card is rarely the answer here.

GLM-10B-unidirectional— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 4. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

GLM-10B-unidirectional— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 203–542 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-10B-unidirectional— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Xeon Phi 5110P, with a memory capacity of 8 GB. It runs the model at a compression of Q4_K_M using about 6.7 GB, and produces roughly 20.3 tokens per second. The number of cards able to run it in total: 509.

GLM-10B-unidirectional— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 339 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: 469.

GLM-10B-unidirectional— how much VRAM does it need?

It needs about 6.7 GB at a compression of Q4_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.

GLM-10B-unidirectional— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q4_K_M, using about 6.7 GB and generating roughly 146 tokens per second. The fit is tight.

GLM-10B-unidirectional— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q6_K, using about 9.1 GB and generating roughly 56.2 tokens per second. The fit is tight.

Source

Original publication

Record last updated 25 May 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