AlbertoB12/Stoicism1_Llama3.1-8b-instruct

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/Stoicism1_Llama3.1-8b-instruct-i1-GGUF: Quantization
• mradermacher/Stoicism1_Llama3.1-8b-instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse