MOSS-Moon-003 TPS calculator

Open weights Fudan University 16B parameters April 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

306 of 818 cards that can run it

Smallest card that fits

P102-101

10 GB · Q3_K_M · 19.5 tok/s

Fastest card

B200

212 tok/s · 180 GB

Which GPUs can run MOSS-Moon-003?

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

306 cards match

Calculating

					Needs	Quantisation	Fit
212 tok/s 127–339 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	17.8 GB	Q8_0	Comfortable
212 tok/s 127–339 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	17.8 GB	Q8_0	Comfortable
169 tok/s 101–271 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	17.8 GB	Q8_0	Comfortable
169 tok/s 101–271 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	17.8 GB	Q8_0	Comfortable
135 tok/s 81–216 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	17.8 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	17.8 GB	Q8_0	Comfortable
129 tok/s 78–207 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	17.8 GB	Q8_0	Comfortable
124 tok/s 74–198 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	17.8 GB	Q8_0	Comfortable
111 tok/s 67–178 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.5 GB	Q3_K_M	Tight
110 tok/s 66–176 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	17.8 GB	Q8_0	Comfortable
110 tok/s 66–176 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	17.8 GB	Q8_0	Comfortable
110 tok/s 66–176 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	17.8 GB	Q8_0	Comfortable
104 tok/s 63–167 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	17.8 GB	Q8_0	Comfortable
88.9 tok/s 53–142 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	17.8 GB	Q8_0	Comfortable
88.9 tok/s 53–142 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	17.8 GB	Q8_0	Comfortable
88.9 tok/s 53–142 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	17.8 GB	Q8_0	Comfortable
88.9 tok/s 53–142 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	17.8 GB	Q8_0	Comfortable
88.9 tok/s 53–142 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	17.8 GB	Q8_0	Comfortable
67.7 tok/s 41–108 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	17.8 GB	Q8_0	Comfortable
67.7 tok/s 41–108 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	17.8 GB	Q8_0	Comfortable
56.4 tok/s 34–90 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	17.8 GB	Q8_0	Comfortable
55.8 tok/s 33–89 · low confidence	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	10.4 GB	Q4_K_M	Tight
55.8 tok/s 33–89 · low confidence	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	10.4 GB	Q4_K_M	Tight
55.2 tok/s 33–88 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	17.8 GB	Q8_0	Comfortable
54.3 tok/s 33–87 · low confidence	CMP 90HX NVIDIA	10 GB	760 GB/s	Jul 2021	8.5 GB	Q3_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: Fudan University
Organisation type: Academia
Country: China
Published: 19 April 2023

What it does

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

Domain: Language
Task: Code generation
Base model: CodeGen-Mono 16.1B

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: 16B
Training data: 700,000,000,000 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: 6.7 × 10²² FLOP
How it was established: Operation counting
Fine-tuning compute: 1.1 × 10²² FLOP

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

Sources

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

Last updated: 28 November 2025

The extremes

The ten fastest GPUs for MOSS-Moon-003

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 MOSS-Moon-003

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

P102-101

Memory needed

8.5 GB

Fastest

212 tok/s

MOSS-Moon-003 is small enough at 16B parameters that hardware is rarely the obstacle — 306 of the cards we track can run it, including cards several years old.

The entry point is the P102-101: 10 GB of memory, Q3_K_M compression, roughly 19.5 tokens per second.

The quickest result comes from a B200 at around 212 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Where it came from

MOSS-Moon-003 was published by Fudan University, in China, in April 2023. It comes out of academia.

It works in Language, and is recorded as doing code generation.

It is derived from CodeGen-Mono 16.1B 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.

Understanding the speeds

Half the cards that hold it manage more than 19.8 tokens per second, and 259 exceed reading speed outright.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

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.

How it was trained

Producing it required around 6.7 × 10²² FLOP of arithmetic, which is a statement about the training budget rather than about inference.

It was trained on about 700,000,000,000 tokens of text.

Step by step

How to choose a GPU for MOSS-Moon-003

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

Every card here has been checked against MOSS-Moon-003 — around 8.5 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context MOSS-Moon-003 can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

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 MOSS-Moon-003 by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for MOSS-Moon-003. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 212 tok/s.
05

Read the fit column last

Tight means MOSS-Moon-003 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

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond MOSS-Moon-003.

Answers

MOSS-Moon-003 — common questions

When was MOSS-Moon-003 released?

MOSS-Moon-003 was published in April 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 MOSS-Moon-003 used for?

MOSS-Moon-003 works in Language, and is recorded as handling code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download MOSS-Moon-003?

The weights for MOSS-Moon-003 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

How much compute was used to train MOSS-Moon-003?

Around 6.7 × 10²² 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.

Can I run MOSS-Moon-003 if it does not fit in my GPU?

It can be split between the card and system memory, but MOSS-Moon-003 generates painfully slowly that way — the nearest miss we calculate is short by 3.2 GB. Nothing on this page assumes offloading.

Would two GPUs run MOSS-Moon-003 faster?

Two cards buy memory rather than speed. That matters for MOSS-Moon-003 only if one card cannot hold it — 306 can, so a second adds little.

Why does the quantisation differ between cards for MOSS-Moon-003?

Because capacity varies, so does how hard MOSS-Moon-003 has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these MOSS-Moon-003 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 127–339 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run MOSS-Moon-003?

The smallest card in our catalogue that holds MOSS-Moon-003 is the P102-101, with 10 GB of memory. It runs the model at Q3_K_M using about 8.5 GB, and produces roughly 19.5 tokens per second. 306 cards in total can run it.

How fast is MOSS-Moon-003 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 212 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 259 of the cards that can run MOSS-Moon-003 clear that.

How much VRAM does MOSS-Moon-003 need?

About 8.5 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 MOSS-Moon-003 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q4_K_M, using about 10.4 GB and generating roughly 55.8 tokens per second — a tight fit.

Can I run MOSS-Moon-003 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 14.1 GB and generating roughly 43.5 tokens per second — a tight fit.

Can I run MOSS-Moon-003 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 17.8 GB and generating roughly 35.5 tokens per second — a comfortable fit.

Is MOSS-Moon-003 open source?

Its weights are published, so MOSS-Moon-003 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 MOSS-Moon-003 have?

MOSS-Moon-003 has 16B parameters. 16B. 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 MOSS-Moon-003?

MOSS-Moon-003 was published by Fudan University, based in China, categorised as academia.

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