Ling-1T TPS calculator
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 cards we hold specifications for
Which GPUs can run Ling-1T?
Set the inputs, read the answer
A longer conversation needs more memory, which can push this model off smaller cards.
Hides cards that would only fit the model by compressing it below this point.
0 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
No card in our catalogue can run this model with these settings. |
|||||||
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
- Ant Group
- Organisation type
- Industry
- Country
- China
- Published
- 10 October 2025
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, Quantitative reasoning, Code generation, Mathematical reasoning
- Numerical format
- FP8
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
- 1T
- Training data
- 20,000,000,000,000 tokens
- Batch size
- 74,317,824
1 trillion total parameters with 50 billion activated parameters
"Pre-trained on 20 trillion+ high-quality, reasoning-dense tokens"
18144 * 4096
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 × 10²⁴ FLOP
- How it was established
- Operation counting
6 FLOP/parameter/token * 50000000000 active parameters * 20000000000000 tokens = 6e+24 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
- Unreleased
- Hugging Face
- inclusionAI
MIT license https://huggingface.co/inclusionAI/Ling-1T
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
- Confident
"We comprehensively evaluated Ling-1T against leading flagship models, including both open-source giants (e.g., DeepSeek-V3.1-Terminus, Kimi-K2-Instruct-0905) and closed-source APIs (GPT-5-main, Gemini-2.5-Pro). Across code generation, software development, competition-level mathematics, professional math, and logical reasoning, Ling-1T consistently demonstrates superior complex reasoning ability and overall advantage."
Sources
Where this record came from and when it was last checked.
- Reference
- Ling-1T
- Last updated
- 18 December 2025
What the numbers mean
What you need to run it
Ling-1T reaches a parameter count of 1T. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 0.
What this model is
Ling-1T was published by Ant Group, in the country recorded as China, during October 2025. It comes out of an organisation categorised as industry.
It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering, Quantitative reasoning, Code generation, Mathematical reasoning.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. On Hugging Face it is published under the organisation inclusionAI.
How it was trained
The training run consumed about 6 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 20,000,000,000,000 tokens of text.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Step by step
How to choose a GPU for Ling-1T
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 Ling-1T. No amount of processing power compensates for a card that cannot hold it.
-
02
Decide how long your conversations run
The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect, because at long context a card that handles short questions easily can be dropped by Ling-1T.
-
03
Set a quality floor
Compression is what makes a model fit smaller cards, at some cost in accuracy. 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
Rank by throughput rather than spec sheet
Sort by speed to see how cards rank for Ling-1T. It will not match a gaming ordering, because generation is bound by memory bandwidth.
-
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 Ling-1T. 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
Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond Ling-1T.
Answers
Ling-1T — common questions
Ling-1T— 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: 0. So a second card is rarely the answer here.
Ling-1T— why does the quantisation differ between cards?
Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.
Ling-1T— how accurate are these speed estimates?
They are calculated from specifications rather than measured, and each carries a range. One example: the range beneath each figure. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
Ling-1T— 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.
Ling-1T— how many parameters does it have?
It has a parameter count of 1T. 1 trillion total parameters with 50 billion activated 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.
Ling-1T— who created it?
It was published by Ant Group, based in China, an organisation categorised as industry.
Ling-1T— when was it released?
It was published in October 2025.
Ling-1T— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering, Quantitative reasoning, Code generation, Mathematical reasoning. 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.
Ling-1T— where can I download it?
Its weights are published on Hugging Face, under the organisation inclusionAI. We do not host model files — this site calculates what hardware is needed to run them.
Ling-1T— how much compute was used to train it?
Training consumed around 6 × 10²⁴ 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.
Ling-1T— can I run it 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 model is rarely worth using. The nearest miss we calculate falls short by 346.5 GB. Every figure here assumes the whole model is resident on the card.
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.