sandbox-ai/Llama-3.1-Tango-8b-Instruct-f16
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-3.1-Tango-8b-Instruct-f16-i1-GGUF: Quantization
- mradermacher/Llama-3.1-Tango-8b-Instruct-f16-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.