Hermes-4-14B-GGUF

Description

Hermes-4-14B-GGUF is an open-weight text-generation model with roughly 14B parameters published by SandLogicTechnologies on the Hugging Face Hub. It has 314 downloads. Runs with transformers.

Categories

• Productivity

Tags

• Qwen3-14B
• qwen3
• hybrid-model
• chatml
• function calling
• Quantization
• Q4_K_M
• Q5_K_M

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: transformers
• 14B parameters