shivnathtathe/nvidia_Riva-Translate-4B-Instruct-v2-GGUF

Riva-Translate-4B-Instruct-v2 GGUF

GGUF quantization of nvidia/Riva-Translate-4B-Instruct-v2.

Supports translation across 36 languages. Trained Nov 2025 – May 2026.

Provided Quants

Usage with llama.cpp

llama-cli -m Riva-Translate-4B-Instruct-v2-Q4_K_M.gguf -p "Translate to French: Hello"

Quantized by @shivnathtathe