Qwen 2.5 on Ollama
Min VRAM: 8 GB
Pull
ollama pull qwen2.5
Run
ollama run qwen2.5
API
After running, Ollama serves an OpenAI-compatible API at http://localhost:11434/v1.
Min VRAM: 8 GB
ollama pull qwen2.5
ollama run qwen2.5
After running, Ollama serves an OpenAI-compatible API at http://localhost:11434/v1.