unsloth/Llama-3.1-8B-unsloth-bnb-4bit
Quantization vs meta-llama/Llama-3.1-8B. unsloth/Llama-3.1-8B-unsloth-bnb-4bit is a quantized version of the other (U8/BF16).
3 derivatives checked
- hendrimardani/fine-tuned-model-indonesian: Quantization
- hendrimardani/fine-tuned-model-indonesian-2: Quantization
- Boobalamurugan/TN_Heritage_LLM: Quantization
1 other repos hold byte-for-byte identical weight files.