rombodawg/Llama-3-8B-Instruct-Coder
Quantization vs unsloth/llama-3-8b-Instruct-bnb-4bit. unsloth/llama-3-8b-Instruct-bnb-4bit is a quantized version of the other (U8/BF16).
5 derivatives checked
- mradermacher/Codellama-3-8B-Finetuned-Instruct-i1-GGUF: Quantization
- QuantFactory/Llama-3-8B-Instruct-Coder-GGUF: Quantization
- mradermacher/Llama-3-8B-Instruct-Coder-i1-GGUF: Quantization
- mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF: Same weights, converted
- mradermacher/Llama-3-8B-Instruct-Coder-GGUF: Quantization
9 other repos hold byte-for-byte identical weight files.