Models / Moonshot AI/ Kimi K2 0905

Kimi K2 0905

Moonshot AI · released Sep 3, 2025 · moonshotai/Kimi-K2-Instruct-0905

Input: text. Output: text.InputOutput
Type
Open weightsCustom licence
Params
1T
Context
262K

32B active per word · about 197K words of context · download allowed, licence restricts use

Our take

We have not written a summary of this model yet.

00

How good is it?

We hold no score for this model.

We look for every model we track on every board we watch, and none of them has turned up Kimi K2 0905 — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.

The boards we watch →

01

Can you run it yourself?

Fits in memory
weights load entirely on the card
Spills to system RAM
some weights offload; much slower
Too large
will not load even with offload
est
size is calculated; the verdict could change by 10%
A card many people ownToo large

GeForce RTX 4090 · 24 GB

Weights at Q4_K_M647.2 / 24 GBest
Usable contextNot calculated for spilled setups
Decode speedNot estimated for spilled setups

Too large for this card. The weights do not fit even with part of them offloaded to system memory.

One step upToo large

Apple M1 Pro (16-core GPU) · 32 GB

Weights at Q4_K_M647.2 / 32 GBest
Usable contextNot calculated for spilled setups
Decode speedNot estimated for spilled setups

Too large for this card. The weights do not fit even with part of them offloaded to system memory.

One step downToo large

Radeon RX 7900 XT · 20 GB

Weights at Q4_K_M647.2 / 20 GBest
Usable contextNot calculated for spilled setups
Decode speedNot estimated for spilled setups

Too large for this card. The weights do not fit even with part of them offloaded to system memory.

Your hardware
Checking your profile…

Memory use by level

Against a 24 GB card.

Q4_K_M
recommended
647.2 GBest
Too large
Q5_K_M
759.3 GBest
Too large
Q8_0
1134.3 GBest
Too large

All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.

Check against your own machine → · All 71 devices, with every size →

02

Or rent it from someone else

Cheapest published offer

Cheapest of 4 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.

per 1M tokens
$0.60 in / $2.50 out
Context served
262K
Throughput
Not measured
Current provider offers with price, context and prompt-privacy answers
ProviderIn / out per 1M tokensContextThroughputTrains on promptsLogs promptsZero retention
OpenRouter$0.60 / $2.50262Knot measuredUnknownUnknownUnknown
Novita AI$0.60 / $2.50262Knot measuredUnknownUnknownUnknown
Novita AIfp8$0.60 / $2.50262K18 tok/sNoNoConfirmed
Groq$1.00 / $3.00262K68 tok/sNoNoUnknown

Across the 4 listings we hold: 2 say they do not train on prompts, 0 say they do and 2 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.

What each host's API supports

From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.

Supported
Not supported
Not published
host gave no parameter list
API features per host
ProviderTool callingJSON outputStrict schema
OpenRouter
Novita AI
Novita AIfp8
Groq

Tool calling: 3 of 4 listings say yes, 1 publishes no parameter list. JSON output: 3 of 4 listings say yes, 1 publishes no parameter list. Strict schema: 3 of 4 listings say yes, 1 publishes no parameter list.

03

Models people weigh against Kimi K2 0905

04

When we formed this view

Dates behind this page

Jul 26, 2026ListedListed on LLMapfirst indexed by our pipeline
Sep 3, 2025AnnouncedKimi K2 0905 announced by Moonshot AI

Prices last checked 4d ago

What we do not know about this model yet

  • We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
  • No board we watch has turned up a score, so we hold no quality figures at all.
  • 1 of 4 listings publish no parameter list, so what their API accepts is unknown to us.
  • Nothing we hold says whether an endpoint streams, so we do not show it either way.
  • 2 of 4 listings do not say whether they train on prompts.
05

Licence and identifiers

What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.

Licence

Custom licence

restricted_openCustom licence — review the terms

This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.

Identifiers

Architecture
Mixture of experts
Modality record
text->text
Catalogue slug
moonshotai-kimi-k2-0905

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us