The nvidia/Riva-Translate-4B-Instruct-v2 galaxy

6 models are built on nvidia/Riva-Translate-4B-Instruct-v2: 6 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 3,836 times in the last 30 days.

Most downloaded direct derivatives

• liodon-ai/Riva-Translate-4B-Instruct-v2-imatrix-GGUF (quantized), 2.1K downloads in 30 days
• shivnathtathe/nvidia_Riva-Translate-4B-Instruct-v2-GGUF (quantized), 391 downloads in 30 days
• kataguru/Riva-Translate-4B-Finnish-GGUF (quantized), 175 downloads in 30 days
• darrowoflykos/Riva-Translate-4B-Instruct-v2-Q8_0-GGUF (quantized), 140 downloads in 30 days
• kataguru/Riva-Translate-4B-Finnish-W4A16-AWQ (quantized), 58 downloads in 30 days
• kataguru/Riva-Translate-4B-Instruct-v2-FP8 (quantized), 31 downloads in 30 days