Product
Kimi K3: Datenblatt, API-Preise und Daten
Updated
Moonshot AIAI Models & LLMs
- Context window
- 1,048,576 tokens
- Open weights (downloadable)
- Yes
Data sheet · Kimi K3
Every figure is quoted from the vendor's official page, with the date we read it. If a row is missing, the source does not state it and we do not estimate it.
Memory and answer length
- Context window
- 1,048,576 tokensRank 5 of 21
What it means and the source
How much text the model keeps in view in a single request, question and answer included. It matters for long documents and whole code projects. A token is a fragment of a word.
huggingface.coOpens the source in a new tab Oct 23, 2026
Knowledge and abilities
- Reads images
- Yes13 models out of 23
What it means and the source
The model can take images (photos, screenshots, charts) as well as text.
huggingface.coOpens the source in a new tab Oct 23, 2026
Size and openness
- Parameters
- 2.8 trillion
What it means and the source
The size of the network: how many billions of learned values make it up. Bigger does not necessarily mean better, but it tells how much hardware it takes to run it yourself.
huggingface.coOpens the source in a new tab Oct 23, 2026- Active parameters per token
- 104 billion
What it means and the source
In «mixture of experts» models only part of the network works on each word: these are the parameters actually used for each token, and they matter for speed and running costs.
huggingface.coOpens the source in a new tab Oct 23, 2026- Open weights (downloadable)
- Yes7 models out of 23
What it means and the source
The model's weights can be downloaded: you can run it on your own servers, adapt it and decide where the data stays, within the licence terms.
huggingface.coOpens the source in a new tab Oct 23, 2026
Where it stands · Kimi K3
The same verified figures, next to those of the other catalogue models. Tap a model for the head-to-head.
Hardware to try AI at home
Kimi K3: just holding the weights in memory takes about 5,600 GB at 16-bit, 2,800 GB at 8-bit, 1,400 GB at 4-bit. Beyond 24 GB it is not a home-PC job: using it through an API makes more sense.Worked out from the billions of parameters the vendor states, not a measurement: context and the runtime need more memory.
Questions and answers
Kimi K3: how much text can it read at once?
The context window is 1,048,576 tokens.
Kimi K3: can I run it on my own computer?
Yes, the vendor publishes the model's weights. Parameters: 2.8 trillion. Holding them in memory takes about 1,400 GB at 4-bit; context and the runtime need more memory.
Kurz gefasst
Bei Moonshot AI Kimi K3 ist Kontextfenster der Wert, auf den es ankommt: 1048576. Ich habe sie von Moonshot AI – model card (Hugging Face) übernommen. Unter den 21, die ich geprüft habe, sind 4 besser. Die andere Zahl, auf die es ankommt, ist Aktive Parameter pro Token (Milliarden): 104B.
Die Zahlen zu Moonshot AI Kimi K3
Ich habe sie nach Gewicht geordnet, mit dem Wert und dem Platz unter den anderen, die ich geprüft habe.
Kontextfenster: 1048576. Platz 5 von 21, die ich verglichen habe.
Aktive Parameter pro Token (Milliarden): 104B. Das ist der beste Wert unter den 2, die ich verglichen habe.
Liest Bilder: 1. Das ist der beste Wert unter den 13, die ich verglichen habe.
Open weights (downloadable): 1. Das ist der beste Wert unter den 7, die ich verglichen habe.
Parameter (Milliarden): 2.8T. Das ist der beste Wert unter den 7, die ich verglichen habe.
Für wen es sich lohnt
Nimm es, wenn Aktive Parameter pro Token (Milliarden) für dich Vorrang hat: 104B — keines der geprüften Modelle ist besser.
Es passt, wenn du Liest Bilder suchst: 1.
Sieh dich anderswo um, wenn dir Kontextfenster wichtig ist: hier sind es 1048576, und 4 Produkte sind besser.
Verwandte Inhalte
Quellen
Ask Sir Compare:Explain these numbers to me
Reviews and tests
Moonshot AI Kimi K3
Reviews and tests · Moonshot AI Kimi K3
Reviews are not available yet.
What changed
- Page updated

Sir Compare’s letter
Updates on AI Models & LLMs? I’ll send them your way.
Pick what you care about: I only write when something new comes out — a guide, a news story, a verified price that drops.
Step 1 of 2
What are you into?
Pick as many as you like. Pick none and you get what’s new in every section.
- Only what you pick
- Never an empty email
- One click to leave