OpenModelsHQ

Kimi-K3

Moonshot AIVisionMoECustom licenseChina Desk

Kimi-K3 is an open-weight vision and language model from Moonshot AI with 2.78T parameters (mixture of experts). At 4-bit it needs about 1858.6 GB of memory, more than any single device in our directory has.

Overview

Estimated memory at 4-bit
1858.6GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
2.78T
Mixture of experts, all weights counted
Context window
1024K
1,048,576 tokens
Cheapest API, blended / 1M
$2.607
₹246 · Wafer · 3:1 input to output
All Moonshot AI API prices

Key information

Lab
Moonshot AI
Released
13 Jun 2026
Parameters
2.78T · MoE
Type
Vision and language
Context
1,048,576 tokens
HF downloads, 30 days
790,518
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
Kimi-K3 needs about 1858.6 GB at 4-bit, 3265.2 GB at 8-bit and 6139.7 GB at 16-bit. At 4-bit it fits none of the reference devices. Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q41858.6 GB
Q83265.2 GB
BF166139.7 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 1858.6 GBToo big 5163%No single device in our directory has enough memory
8-bit (Q8)≈ 3265.2 GBToo big 9070%No single device in our directory has enough memory
16-bit (BF16)≈ 6139.7 GBToo big 17055%No single device in our directory has enough memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

No trusted MLX build found yet.

Check your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

unsloth/Kimi-K3-GGUFFind compatible hardware

Through an API

Wafer (mxfp4) is the cheapest provider we found.

$0.276 / $9.60

Input / output per 1M tokens
₹26 / ₹905 at ₹94.29 per $1

Blended: $2.607 (₹246) per 1M. Ranked by a 3:1 mix of input and output tokens.

GGUF with llama.cppView repository
llama-cli -hf unsloth/Kimi-K3-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of llama.cpp. We have not run them; check each repository for available files.

Hosted API 20

USD and INR per million tokensAll Moonshot AI API prices
Precision
WaferCheapest$2.607₹246$0.276₹26$9.60₹9051,048,576MXFP4
Relace$2.8882₹272$0.1824₹17$11.0055₹1,0381,048,576FP4
Chutes$3.7625₹355$1.85₹174$9.50₹8961,048,576MXFP4
InferenceNet$3.9255₹370$0.234₹22$15.00₹1,4141,048,576FP4
Sail Research$4.4037₹415$0.345₹33$16.58₹1,5631,048,576FP4
Makora$4.90₹462$1.20₹113$16.00₹1,5091,048,576FP4
DigitalOcean$5.15₹486$2.55₹240$12.95₹1,2211,048,576Not listed
Io Net$5.225₹493$2.30₹217$14.00₹1,3201,048,320FP4
DeepInfra$5.70₹537$2.85₹269$14.25₹1,3441,048,576MXFP4
Amazon Bedrock$6.00₹566$3.00₹283$15.00₹1,4141,048,576Not listed
BaseTen$6.00₹566$3.00₹283$15.00₹1,4141,048,576FP8
Fireworks$6.00₹566$3.00₹283$15.00₹1,4141,048,576Not listed
KT$6.00₹566$3.00₹283$15.00₹1,4141,048,576Not listed
Modal$6.00₹566$3.00₹283$15.00₹1,4141,048,576MXFP4
Moonshot AI$6.00₹566$3.00₹283$15.00₹1,4141,048,576Not listed
Nebius$6.00₹566$3.00₹283$15.00₹1,4141,048,576FP4
Parasail$6.00₹566$3.00₹283$15.00₹1,4141,048,576FP4
River$6.00₹566$3.00₹283$15.00₹1,4141,048,576Not listed
Together$6.00₹566$3.00₹283$15.00₹1,4141,048,576Not listed
Alibaba$6.90₹651$3.45₹325$17.25₹1,6271,048,576Not listed
View on OpenRouterEndpoint sourceSorted by the blended price: 3 parts input to 1 part output. Context limits differ by provider.

INR at ₹94.29 per $1. Prices fetched 14 Nov 2026.

More about this model

Frequently asked questions

How much memory does Kimi-K3 need? At an 8k context, about 1858.6 GB at 4-bit, 3265.2 GB at 8-bit and 6139.7 GB at 16-bit (BF16). A longer context needs more.

Can I run Kimi-K3 on a Mac? No Mac in our directory has enough usable memory for the 4-bit estimate of 1858.6 GB. We have not found a trusted MLX build yet, but a GGUF build is available.

Does the full context fit? Kimi-K3 supports up to 1,048,576 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? The cheapest provider we found is Wafer, at $0.28 per 1M input tokens and $9.60 per 1M output tokens (₹26 and ₹905 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens.

License in plain English

Custom license. This model uses a custom license rather than a standard one. Read it on the model card before using the model commercially. This summary is not legal advice.

Read the license on the model card

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card, GGUF repository, OpenRouter.