Riva-Translate-4B-Instruct-v2-imatrix-GGUF

Description

Riva-Translate-4B-Instruct-v2-imatrix-GGUF is an open-weight text-generation model with roughly 4B parameters published by liodon-ai on the Hugging Face Hub. It has 372 downloads.

Categories

• Productivity

Tags

• local-llm
• llama.cpp
• lm-studio
• quantized
• imatrix
• sub-4-bit
• mistral
• text-generation

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• 4B parameters