Qwen3-VL-30B-A3B-Instruct-GGUF

30B open-weight model from Qwen for local AI inference.

Run Qwen3-VL-30B-A3B-Instruct-GGUF locally with Ollama: ollama pull qwen3-vl-30b-a3b:30b

Minimum 24GB RAM. Context length: 4096 tokens.