EpistemeAI/OpenCodeLlama-3.1-8B

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

1 derivatives checked

• mradermacher/OpenCodeLlama-3.1-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse