OpenModelsHQ

Kimi-K2-Thinking

Moonshot AILLMMoEModified MITChina Desk

Kimi-K2-Thinking is an open-weight language model from Moonshot AI with 1.03T parameters (mixture of experts). At 4-bit it needs about 693.2 GB of memory, more than any single device in our directory has.

Overview

Estimated memory at 4-bit
693.2GB

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

Total parameters
1.03T
Mixture of experts, all weights counted
Context window
256K
262,144 tokens
Cheapest API, blended / 1M
$1.075
₹101 · Novita · 3:1 input to output
All Moonshot AI API prices

Key information

Lab
Moonshot AI
Released
4 Nov 2025
Parameters
1.03T · MoE
Type
Language
Context
262,144 tokens
HF downloads, 30 days
54,497
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
Kimi-K2-Thinking needs about 693.2 GB at 4-bit, 1212.6 GB at 8-bit and 2273.9 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
Q4693.2 GB
Q81212.6 GB
BF162273.9 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)≈ 693.2 GBToo big 1926%No single device in our directory has enough memory
8-bit (Q8)≈ 1212.6 GBToo big 3368%No single device in our directory has enough memory
16-bit (BF16)≈ 2273.9 GBToo big 6316%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

Start with the MLX files, built for Apple Silicon.

mlx-community/Kimi-K2-ThinkingCheck your Mac

With GGUF

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

unsloth/Kimi-K2-Thinking-GGUFFind compatible hardware

Through an API

Novita (bf16) is the cheapest provider we found.

$0.60 / $2.50

Input / output per 1M tokens
₹57 / ₹236 at ₹94.29 per $1

Blended: $1.075 (₹101) per 1M. Ranked by a 3:1 mix of input and output tokens.

MLX on Apple SiliconView repository
mlx_lm.generate --model mlx-community/Kimi-K2-Thinking \
  --prompt "Explain how a transformer works."
GGUF with llama.cppView repository
llama-cli -hf unsloth/Kimi-K2-Thinking-GGUF \
  -c 8192 -p "Explain how a transformer works."

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

Hosted API 1

USD and INR per million tokensAll Moonshot AI API prices
Precision
NovitaCheapest$1.075₹101$0.60₹57$2.50₹236262,144BF16
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-K2-Thinking need? At an 8k context, about 693.2 GB at 4-bit, 1212.6 GB at 8-bit and 2273.9 GB at 16-bit (BF16). A longer context needs more.

Can I run Kimi-K2-Thinking on a Mac? No Mac in our directory has enough usable memory for the 4-bit estimate of 693.2 GB. An MLX build is available: mlx-community/Kimi-K2-Thinking.

Does the full context fit? Kimi-K2-Thinking supports up to 262,144 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 Novita, at $0.60 per 1M input tokens and $2.50 per 1M output tokens (₹57 and ₹236 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens.

License in plain English

Modified MIT. This model adds conditions to the MIT license. The conditions differ by model; read its own license before commercial use. 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