27B open-weight model from prism-ml for local AI inference.
Run Bonsai-27B-gguf locally with Ollama: ollama pull bonsai-27b:27b
Minimum 24GB RAM. Context length: 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
Minimum 24GB RAM. Context length: 4096 tokens.