AI Agent Hub
Back to models
🤖

Kimi-VL-A3B-Thinking

Multimodal Released 2025-04-09

About this model

Technical Specs

  • Architecture: Transformer
  • Input Modalities: text

Hardware Requirements

  • API-only (no local hardware needed)

Related Models

🤖
gemma-4-31B-it
gemma-4-31B-it

Multimodal 30.7B ↓ 8.3M
🤖
Qwen3-VL-8B-Instruct
Qwen3-VL-8B-Instruct

Multimodal 8.8B ↓ 9M
🤖
Qwen2.5-VL-7B-Instruct
Qwen2.5-VL-7B-Instruct

Multimodal 7.0B ↓ 8.1M
🤖
Qwen3.5-9B
Qwen3.5-9B

Multimodal 9.0B ↓ 12.6M