← All Models | Other Chinese/Asian AI Labs:

moonshotai/Kimi-K2.5

📊 Model Parameters

Total Parameters 0
Context Length 2,048
Hidden Size 0
Layers 0
Attention Heads 0
KV Heads 0

💾 Memory Requirements

FP32 (Full) 0.0 MB
FP16 (Half) 0.0 MB
INT8 (Quantized) 0.0 MB
INT4 (Quantized) 0.0 MB

🔑 KV Cache (Inference)

Per Token (FP16) 0 B
Max Context FP32 0.0 MB
Max Context FP16 0.0 MB
Max Context INT8 0.0 MB

⚙️ Model Configuration

Attention Configuration

Tied EmbeddingsNo

Special Tokens

Pad Token ID163,839
BOS Token ID163,584
EOS Token ID163585

Data Type

Model Dtypebfloat16
Layer Types:
Attention
MLP/FFN
Normalization
Embedding