QomSSLab/LLama-Rhino-8B-RAG

Quantization vs unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit. unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit is a quantized version of the other (U8/BF16).

2 derivatives checked

• mradermacher/LLama-Rhino-8B-RAG-i1-GGUF: Quantization
• mradermacher/LLama-Rhino-8B-RAG-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse