HGRN 1B (WT 103) TPS calculator

Open weights Shanghai AI Lab,Massachusetts Institute of Technology (MIT) 1B parameters November 2023

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

818 of 818 cards that can run it

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 36.9 tok/s

Fastest card

B200

3,388 tok/s · 180 GB

Which GPUs can run HGRN 1B (WT 103)?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
3,388 tok/s 2,033–5,421 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.8 GB	Q8_0	Comfortable
3,388 tok/s 2,033–5,421 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.8 GB	Q8_0	Comfortable
2,706 tok/s 1,623–4,329 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.8 GB	Q8_0	Comfortable
2,706 tok/s 1,623–4,329 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.8 GB	Q8_0	Comfortable
2,164 tok/s 1,298–3,462 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
2,071 tok/s 1,243–3,314 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.8 GB	Q8_0	Comfortable
2,071 tok/s 1,243–3,314 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.8 GB	Q8_0	Comfortable
1,982 tok/s 1,189–3,171 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,669 tok/s 1,001–2,670 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,084 tok/s 650–1,734 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.8 GB	Q8_0	Comfortable
1,084 tok/s 650–1,734 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.8 GB	Q8_0	Comfortable
903 tok/s 542–1,445 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
884 tok/s 530–1,414 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.8 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: Shanghai AI Lab,Massachusetts Institute of Technology (MIT)
Organisation type: Academia,Academia
Country: China, United States of America
Published: 8 November 2023
Authors: Zhen Qin, Songlin Yang, Yiran Zhong

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

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: 1B
Training data: 100,000,000,000 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: 2 × 10¹⁹ 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.

Training hardware: NVIDIA A100
Chips used: 8
Power draw: 6.3 kW

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)
Hugging Face: OpenNLPLab

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: Hierarchically Gated Recurrent Neural Network for Sequence Modeling
Last updated: 11 February 2026

The extremes

The ten fastest GPUs for HGRN 1B (WT 103)

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 HGRN 1B (WT 103)

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

Tesla C1080

Memory needed

1.8 GB

Fastest

3,388 tok/s

HGRN 1B (WT 103) is small enough at 1B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q8_0 compression, giving roughly 36.9 tokens per second.

At the other end, a B200 generates roughly 3,388 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

HGRN 1B (WT 103) was published by Shanghai AI Lab,Massachusetts Institute of Technology (MIT), in China, in November 2023. It comes out of academia,Academia.

It works in Language, and is recorded as doing language modeling/generation, Question answering.

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 OpenNLPLab organisation on Hugging Face.

Understanding the speeds

The median result is around 95.1 tokens per second; 806 cards produce text faster than most people read it.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

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.

How it was trained

Training it took roughly 2 × 10¹⁹ FLOP of computation, on NVIDIA A100 — a measure of what producing the model cost, not of how fast it answers.

Around 100,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for HGRN 1B (WT 103)

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 HGRN 1B (WT 103) — around 1.8 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
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 HGRN 1B (WT 103) stops fitting a card that seemed fine.
03

Set a quality floor

Compression is what makes HGRN 1B (WT 103) fit smaller cards, at some cost in accuracy — Q8_0 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 HGRN 1B (WT 103). It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 3,388 tok/s.
05

Check the fit verdict before buying

A tight fit runs HGRN 1B (WT 103) but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
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 HGRN 1B (WT 103) is settled.

Answers

HGRN 1B (WT 103) — common questions

Is HGRN 1B (WT 103) open source?

Its weights are published, so HGRN 1B (WT 103) 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 HGRN 1B (WT 103) have?

HGRN 1B (WT 103) has 1B parameters. 1B (table 4 and hugging face repo). 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 HGRN 1B (WT 103)?

HGRN 1B (WT 103) was published by Shanghai AI Lab,Massachusetts Institute of Technology (MIT), based in China, categorised as academia,Academia.

When was HGRN 1B (WT 103) released?

HGRN 1B (WT 103) was published in November 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

What is HGRN 1B (WT 103) used for?

HGRN 1B (WT 103) works in Language, and is recorded as handling language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download HGRN 1B (WT 103)?

Its weights are published under the OpenNLPLab 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 HGRN 1B (WT 103)?

Around 2 × 10¹⁹ FLOP, on NVIDIA A100. 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 HGRN 1B (WT 103) 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 HGRN 1B (WT 103) is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run HGRN 1B (WT 103) faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run HGRN 1B (WT 103) alone, the case for pairing is weak.

Why does the quantisation differ between cards for HGRN 1B (WT 103)?

Because capacity varies, so does how hard HGRN 1B (WT 103) has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these HGRN 1B (WT 103) 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 2,033–5,421 tok/s on the B200 rather than a single number.

What GPU do I need to run HGRN 1B (WT 103)?

The smallest card in our catalogue that holds HGRN 1B (WT 103) is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.8 GB, and produces roughly 36.9 tokens per second. 818 cards in total can run it.

How fast is HGRN 1B (WT 103) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 3,388 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 806 of the cards that can run HGRN 1B (WT 103) clear that.

How much VRAM does HGRN 1B (WT 103) need?

About 1.8 GB at Q8_0 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.

Can I run HGRN 1B (WT 103) on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.8 GB and generating roughly 631 tokens per second — a comfortable fit.

Can I run HGRN 1B (WT 103) on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.8 GB and generating roughly 386 tokens per second — a comfortable fit.

Can I run HGRN 1B (WT 103) on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.8 GB and generating roughly 479 tokens per second — a comfortable fit.

Can I run HGRN 1B (WT 103) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.8 GB and generating roughly 568 tokens per second — a comfortable fit.

Source

Original publication

Record last updated 11 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