SPHINX (Llama 2 13B) TPS calculator

Open weights Shanghai AI Lab,Chinese University of Hong Kong (CUHK),ShanghaiTech University 19.9B 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

293 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Quadro K6000

12 GB · Q3_K_M · 14.1 tok/s

Fastest card

B200

170 tok/s · 180 GB

Which GPUs can run SPHINX (Llama 2 13B)?

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

293 cards match

Calculating

					Needs	Quantisation	Fit
170 tok/s 102–272 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	22.0 GB	Q8_0	Comfortable
170 tok/s 102–272 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	22.0 GB	Q8_0	Comfortable
136 tok/s 82–218 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	22.0 GB	Q8_0	Comfortable
136 tok/s 82–218 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	22.0 GB	Q8_0	Comfortable
109 tok/s 65–174 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	22.0 GB	Q8_0	Comfortable
104 tok/s 62–167 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	22.0 GB	Q8_0	Comfortable
104 tok/s 62–167 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	22.0 GB	Q8_0	Comfortable
99.6 tok/s 60–159 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	22.0 GB	Q8_0	Comfortable
88.4 tok/s 53–141 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	22.0 GB	Q8_0	Comfortable
88.4 tok/s 53–141 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	22.0 GB	Q8_0	Comfortable
88.4 tok/s 53–141 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	22.0 GB	Q8_0	Comfortable
83.9 tok/s 50–134 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	22.0 GB	Q8_0	Comfortable
71.5 tok/s 43–114 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	22.0 GB	Q8_0	Comfortable
71.5 tok/s 43–114 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	22.0 GB	Q8_0	Comfortable
71.5 tok/s 43–114 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	22.0 GB	Q8_0	Comfortable
71.5 tok/s 43–114 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	22.0 GB	Q8_0	Comfortable
71.5 tok/s 43–114 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	22.0 GB	Q8_0	Comfortable
55.5 tok/s 33–89 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	12.7 GB	Q4_K_M	Tight
54.5 tok/s 33–87 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	22.0 GB	Q8_0	Comfortable
54.5 tok/s 33–87 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	22.0 GB	Q8_0	Comfortable
52.4 tok/s 31–84 · low confidence	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	10.4 GB	Q3_K_M	Tight
52.4 tok/s 31–84 · low confidence	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	10.4 GB	Q3_K_M	Tight
47.2 tok/s 28–75 · low confidence	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	12.7 GB	Q4_K_M	Tight
45.4 tok/s 27–73 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	22.0 GB	Q8_0	Comfortable
44.4 tok/s 27–71 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	22.0 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: Shanghai AI Lab,Chinese University of Hong Kong (CUHK),ShanghaiTech University
Organisation type: Academia,Academia,Academia
Country: China, Hong Kong
Published: 13 November 2023
Authors: Ziyi Lin, Chris Liu, Renrui Zhang, Peng Gao, Longtian Qiu, Han Xiao, Han Qiu, Chen Lin, Wenqi Shao, Keqin Chen, Jiaming Han, Siyuan Huang, Yichi Zhang, Xuming He, Hongsheng Li, Yu Qiao

What it does

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

Domain: Vision, Language, Multimodal
Task: Visual question answering, Image captioning
Base model: Llama 2-13B
Numerical format: BF16

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: 19.9B
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.

Training compute: 3 × 10²² FLOP
How it was established: Hardware
Fine-tuning compute: 4 × 10²¹ 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 40 GB
Chips used: 32
Chip-hours: 9,280
Wall-clock time: 290 hours (12.1 days)
Power draw: 25.4 kW
Compute cost: $239,189

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: Open (restricted use)
Hugging Face: Alpha-VLLM

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: SOTA improvement
Record confidence: Likely

Sources

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

Reference: SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
Last updated: 11 February 2026

The extremes

The ten fastest GPUs that run SPHINX (Llama 2 13B)

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 SPHINX (Llama 2 13B)

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

Hardware requirements in practice

Minimum card

Quadro K6000

Memory needed

10.4 GB

Fastest

170 tok/s

SPHINX (Llama 2 13B) is small enough at 19.9B parameters that hardware is rarely the obstacle — 293 of the cards we track can run it, including cards several years old.

The entry point is the Quadro K6000: 12 GB of memory, Q3_K_M compression, roughly 14.1 tokens per second.

A B200 is the fastest we calculate for it: about 170 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

SPHINX (Llama 2 13B) was published by Shanghai AI Lab,Chinese University of Hong Kong (CUHK),ShanghaiTech University, in China, in November 2023. The organisation is categorised as academia,Academia,Academia.

It works in Vision, Language, Multimodal, and is recorded as doing visual question answering, Image captioning.

It is derived from Llama 2-13B rather than trained from scratch, which is the usual way a specialised model is produced.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the Alpha-VLLM organisation on Hugging Face.

Understanding the speeds

The median result is around 20.7 tokens per second; 248 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.

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.

What went into building it

Producing it required around 3 × 10²² FLOP of arithmetic, on NVIDIA A100 SXM4 40 GB, which is a statement about the training budget rather than about inference.

The reason it appears in this catalogue at all is sOTA improvement.

Step by step

How to choose a GPU for SPHINX (Llama 2 13B)

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

Every card here has been checked against SPHINX (Llama 2 13B) — around 10.4 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
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 SPHINX (Llama 2 13B) stops fitting a card that seemed fine.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage SPHINX (Llama 2 13B) by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for SPHINX (Llama 2 13B) follows memory bandwidth, not core counts, which is why the B200 tops it at 170 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs SPHINX (Llama 2 13B) but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

See what else that card runs

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond SPHINX (Llama 2 13B).

Answers

SPHINX (Llama 2 13B) — common questions

Can I run SPHINX (Llama 2 13B) on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q3_K_M, using about 10.4 GB and generating roughly 52.4 tokens per second — a tight fit.

Can I run SPHINX (Llama 2 13B) on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q4_K_M, using about 12.7 GB and generating roughly 55.5 tokens per second — a tight fit.

Can I run SPHINX (Llama 2 13B) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q6_K, using about 17.4 GB and generating roughly 41.4 tokens per second — a comfortable fit.

Is SPHINX (Llama 2 13B) open source?

Its weights are published, so SPHINX (Llama 2 13B) 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 SPHINX (Llama 2 13B) have?

SPHINX (Llama 2 13B) has 19.9B parameters. SPHINX + Llama 2 13B SPHINX component involves four vision encoders: - CLIP - ViT - CLIP - ConvNeXt V2 (89M to 659M params, depending on size) - DinoV2 - ViT (22M to 1.14B params, depending on size) - Q-former (188M params) Also involves to projection networks Huggingface Hub model files appear to be 39.8GB. Assuming models are stored in fp16 there are 2 bytes per parameter, so 39.8 / 2 = 19.9B 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 SPHINX (Llama 2 13B)?

SPHINX (Llama 2 13B) was published by Shanghai AI Lab,Chinese University of Hong Kong (CUHK),ShanghaiTech University, based in China, categorised as academia,Academia,Academia.

When was SPHINX (Llama 2 13B) released?

SPHINX (Llama 2 13B) 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 SPHINX (Llama 2 13B) used for?

SPHINX (Llama 2 13B) works in Vision, Language, Multimodal, and is recorded as handling visual question answering, Image captioning. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download SPHINX (Llama 2 13B)?

Its weights are published under the Alpha-VLLM 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 SPHINX (Llama 2 13B)?

Around 3 × 10²² FLOP, on NVIDIA A100 SXM4 40 GB. 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 SPHINX (Llama 2 13B) 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 SPHINX (Llama 2 13B) is rarely worth using — the nearest miss we calculate is short by 2.8 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run SPHINX (Llama 2 13B) faster?

Two cards buy memory rather than speed. That matters for SPHINX (Llama 2 13B) only if one card cannot hold it — 293 can, so a second adds little.

Why does the quantisation differ between cards for SPHINX (Llama 2 13B)?

Because capacity varies, so does how hard SPHINX (Llama 2 13B) has to be squeezed — 4 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these SPHINX (Llama 2 13B) speed estimates?

These are estimates with real error bars. The fastest result here, 102–272 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 SPHINX (Llama 2 13B)?

The smallest card in our catalogue that holds SPHINX (Llama 2 13B) is the Quadro K6000, with 12 GB of memory. It runs the model at Q3_K_M using about 10.4 GB, and produces roughly 14.1 tokens per second. 293 cards in total can run it.

How fast is SPHINX (Llama 2 13B) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 170 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 248 of the cards that can run SPHINX (Llama 2 13B) clear that.

How much VRAM does SPHINX (Llama 2 13B) need?

About 10.4 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.

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