Skip to main content

Available Models

Currently, the following AI models are supported:

Language Models​

Local Models​

  • small-icon Qwen3
    • Qwen/Qwen3-0.6B
    • Qwen/Qwen3-1.7B
    • Qwen/Qwen3-4B
    • Qwen/Qwen3-8B
    • Qwen/Qwen3-14B
    • Qwen/Qwen3-32B
    • Qwen/Qwen3-30B-A3B (MoE)

API Models​

  • small-icon OpenAI
  • small-icon Gemini
  • small-icon Claude
  • small-icon Grok

Embedding Models​

Local Models​

  • small-icon BAAI/bge-m3

VRAM requirements​

These values may vary depending on the environment and circumstances.

Requirements for available VRAM size by models are estimated as follows:

ModelContext lengthVRAM (params)VRAM (total)
BAAI/bge-m38k≈ 0.3 GB≈ 0.3 GB
Qwen/Qwen3-0.6B40k≈ 0.5 GB≈ 5.0 GB
Qwen/Qwen3-1.7B40k≈ 1.0 GB≈ 5.5 GB
Qwen/Qwen3-4B40k≈ 2.4 GB≈ 8.0 GB
Qwen/Qwen3-8B40k≈ 4.5 GB≈ 10.5 GB
Qwen/Qwen3-14B40k≈ 8.0 GB≈ 14.5 GB
Qwen/Qwen3-32B40k≈ 17.6 GB≈ 25 GB
Qwen/Qwen3-30B-A3B40k≈ 16.5 GB≈ 24 GB