LLaVA-NeXT-32B-Qwen TPS calculator

Open weights LMMs-Lab 32B parameters July 2024

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

132 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX A4500

20 GB · Q3_K_M · 22.9 tok/s

Fastest card

B200

106 tok/s · 180 GB

Which GPUs can run LLaVA-NeXT-32B-Qwen?

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

132 cards match

Calculating

					Needs	Quantisation	Fit
106 tok/s 64–169 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	35.0 GB	Q8_0	Comfortable
106 tok/s 64–169 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	35.0 GB	Q8_0	Comfortable
84.6 tok/s 51–135 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	35.0 GB	Q8_0	Comfortable
84.6 tok/s 51–135 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	35.0 GB	Q8_0	Comfortable
67.6 tok/s 41–108 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	35.0 GB	Q8_0	Comfortable
64.7 tok/s 39–104 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.0 GB	Q8_0	Comfortable
64.7 tok/s 39–104 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.0 GB	Q8_0	Comfortable
61.9 tok/s 37–99 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	35.0 GB	Q8_0	Comfortable
55.0 tok/s 33–88 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	35.0 GB	Q8_0	Comfortable
55.0 tok/s 33–88 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	35.0 GB	Q8_0	Comfortable
55.0 tok/s 33–88 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	35.0 GB	Q8_0	Comfortable
52.2 tok/s 31–83 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	35.0 GB	Q8_0	Comfortable
44.5 tok/s 27–71 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.0 GB	Q8_0	Comfortable
44.5 tok/s 27–71 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	35.0 GB	Q8_0	Comfortable
44.5 tok/s 27–71 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	35.0 GB	Q8_0	Comfortable
44.5 tok/s 27–71 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.0 GB	Q8_0	Comfortable
44.5 tok/s 27–71 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	35.0 GB	Q8_0	Comfortable
40.9 tok/s 25–66 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	20.1 GB	Q4_K_M	Tight
37.3 tok/s 22–60 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	20.1 GB	Q4_K_M	Tight
36.0 tok/s 22–58 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	27.5 GB	Q6_K	Tight
36.0 tok/s 22–58 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	27.5 GB	Q6_K	Tight
34.4 tok/s 21–55 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	27.5 GB	Q6_K	Tight
34.4 tok/s 21–55 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	27.5 GB	Q6_K	Tight
33.9 tok/s 20–54 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	35.0 GB	Q8_0	Comfortable
33.9 tok/s 20–54 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	35.0 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: LMMs-Lab
Organisation type: Research collective
Published: 16 July 2024

What it does

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

Domain: Multimodal, Language
Task: Chat, Language modeling/generation, Visual question answering, Image captioning
Base model: Qwen1.5-32B

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: 32B
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.

How it was established: Hardware
Fine-tuning compute: 7.5 × 10²⁰ FLOP

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 SXM4 80 GB
Chips used: 64
Wall-clock time: 35 hours
Power draw: 50.5 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 (restricted use)
Training code: Unreleased
Hugging Face: lmms-lab

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: Github: lmms-lab/llava-next-qwen-32b
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run LLaVA-NeXT-32B-Qwen

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 LLaVA-NeXT-32B-Qwen

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

The hardware side

Minimum card

RTX A4500

Memory needed

16.3 GB

Fastest

106 tok/s

With 32B parameters, LLaVA-NeXT-32B-Qwen lands in the range a serious desktop card can handle once the weights are compressed. 132 of the cards we track can run it.

At the low end, a RTX A4500 handles it — 20 GB, at Q3_K_M, for about 22.9 tokens per second.

At the other end, a B200 generates roughly 106 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Background

LLaVA-NeXT-32B-Qwen was published by LMMs-Lab, in July 2024. The organisation is categorised as research collective.

It works in Multimodal, Language, and is recorded as doing chat, Language modeling/generation, Visual question answering, Image captioning.

Its starting point was Qwen1.5-32B — most models at this scale are adapted from an existing base rather than built from nothing.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the lmms-lab organisation on Hugging Face.

Reading the throughput figures

The median result is around 20.7 tokens per second; 103 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.

Step by step

How to choose a GPU for LLaVA-NeXT-32B-Qwen

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

01

Check what it needs before anything else

The table lists every card that can hold LLaVA-NeXT-32B-Qwen — around 16.3 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
02

Decide how long your conversations run

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason LLaVA-NeXT-32B-Qwen stops fitting a card that seemed fine.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of LLaVA-NeXT-32B-Qwen — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Ranking by tokens per second for LLaVA-NeXT-32B-Qwen follows memory bandwidth, not core counts, which is why the B200 tops it at 106 tok/s.
05

Read the fit column last

Tight means LLaVA-NeXT-32B-Qwen loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
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. Worth a look before buying for LLaVA-NeXT-32B-Qwen alone — a card is usually bought for more than one model.

Answers

LLaVA-NeXT-32B-Qwen — common questions

Is LLaVA-NeXT-32B-Qwen open source?

Its weights are published, so LLaVA-NeXT-32B-Qwen 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 LLaVA-NeXT-32B-Qwen have?

LLaVA-NeXT-32B-Qwen has 32B parameters. 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 LLaVA-NeXT-32B-Qwen?

LLaVA-NeXT-32B-Qwen was published by LMMs-Lab, categorised as research collective.

When was LLaVA-NeXT-32B-Qwen released?

LLaVA-NeXT-32B-Qwen was published in July 2024. 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 LLaVA-NeXT-32B-Qwen used for?

LLaVA-NeXT-32B-Qwen works in Multimodal, Language, and is recorded as handling chat, Language modeling/generation, Visual question answering, Image captioning. 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.

Where can I download LLaVA-NeXT-32B-Qwen?

Its weights are published under the lmms-lab organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

Can I run LLaVA-NeXT-32B-Qwen if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down — the nearest miss we calculate is short by 5.7 GB. Our figures for LLaVA-NeXT-32B-Qwen assume it is fully resident.

Would two GPUs run LLaVA-NeXT-32B-Qwen faster?

A second card roughly doubles the memory available but not the generation rate. With 132 cards already able to run LLaVA-NeXT-32B-Qwen alone, the case for pairing is weak.

Why does the quantisation differ between cards for LLaVA-NeXT-32B-Qwen?

Each card is shown running the least-compressed copy it can hold, and LLaVA-NeXT-32B-Qwen appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these LLaVA-NeXT-32B-Qwen speed estimates?

These are estimates with real error bars. The fastest result here, 64–169 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run LLaVA-NeXT-32B-Qwen?

The smallest card in our catalogue that holds LLaVA-NeXT-32B-Qwen is the RTX A4500, with 20 GB of memory. It runs the model at Q3_K_M using about 16.3 GB, and produces roughly 22.9 tokens per second. 132 cards in total can run it.

How fast is LLaVA-NeXT-32B-Qwen on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 106 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 103 of the cards that can run LLaVA-NeXT-32B-Qwen clear that.

How much VRAM does LLaVA-NeXT-32B-Qwen need?

About 16.3 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.

Can I run LLaVA-NeXT-32B-Qwen on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 20.1 GB and generating roughly 40.9 tokens per second — a tight fit.

Source

Original publication

Record last updated 28 November 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.

All AI models