Kimi K2-Base
Active Parameters
1T
Context Length
128K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
Modified MIT License
Release Date
11 Jul 2025
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.57 · Output: $2.30
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
140x RTX 4090
24GB VRAM
Datacenter
34x NVIDIA A100
80GB VRAM
Apple Silicon
30x Apple M3 Max
128GB VRAM
128,000 tokens
Consumer
162x RTX 4090
24GB VRAM
Datacenter
39x NVIDIA A100
80GB VRAM
Apple Silicon
35x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#103
| Benchmark | Score | Rank |
|---|---|---|
Software Engineering | 0.71 | 13 |
Professional Knowledge | 0.692 | 43 |
General Text | 1418 | 82 |
Graduate-Level QA | 0.481 | 106 |
Intelligence Index | 0.13 | 159 |
General Knowledge Reference | 0.878 | 6 |
Rankings
Overall Rank
#103
Coding Rank
#41
About Kimi K2-Base
Kimi K2-Base is Moonshot AI's foundational 1T-parameter Mixture-of-Experts base model activating 32B parameters per token. Pretrained on 15.5T tokens, it provides a highly capable platform for fine-tuning complex reasoning and agentic workflows.
Technical Specifications
Attention
Attention Structure
Multi-Layer Attention
Attention Heads
64
Key-Value Heads
64
Attention Head Dimension
-
Position Embedding
ROPE
RoPE Theta
50,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
7,168
Number of Layers
61
FFN Intermediate Size (Dense)
2,048
Multi-Token Prediction Heads
0
Tokenizer
Vocabulary Size
163,840
Mixture of Experts
Total Expert Parameters
32.0B
Number of Experts
384
Active Experts
8
Shared Experts
1
FFN Intermediate Size (per Expert)
2,048
Dense Layers Before MoE
1
About Kimi K2
Moonshot AI's Kimi K2 is a Mixture-of-Experts model featuring one trillion total parameters, activating 32 billion per token. Designed for agentic intelligence, it utilizes a sparse architecture with 384 experts and the MuonClip optimizer for training stability, supporting a 128K token context window.