K2 Horizon MoVA 36B A4B
Active Parameters
36B
Context Length
524K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
Apache 2.0
Release Date
1 Sept 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Self-hosted only
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
4x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
524,288 tokens
Consumer
9x RTX 4090
24GB VRAM
Datacenter
3x NVIDIA A100
80GB VRAM
Apple Silicon
2x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
No evaluation benchmarks for K2 Horizon MoVA 36B A4B available.
Rankings
Overall Rank
-
Coding Rank
-
About K2 Horizon MoVA 36B A4B
K2 Horizon MoVA 36B A4B is a mixture-of-experts language model activating 4B parameters per token for efficient high-capacity inference. It is optimized for complex problem-solving, context retention, and reasoning tasks.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
32
Key-Value Heads
8
Attention Head Dimension
128
Position Embedding
ROPE
RoPE Theta
10,000,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
No
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
2,560
Number of Layers
48
FFN Intermediate Size (Dense)
6,144
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
250,624
Mixture of Experts
Total Expert Parameters
4.0B
Number of Experts
100
Active Experts
8
Shared Experts
1
FFN Intermediate Size (per Expert)
768
Dense Layers Before MoE
-
Resources
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.