27B open-weight model from prism-ml for local AI inference.
Run Bonsai-27B-gguf locally with Ollama: ollama pull bonsai-27b:27b
Mínimo 24 GB de RAM. Longitud del contexto: 4096 tokens.
27B open-weight model from prism-ml for local AI inference.
Run Bonsai-27B-gguf locally with Ollama: ollama pull bonsai-27b:27b
Mínimo 24 GB de RAM. Longitud del contexto: 4096 tokens.