mradermacher/RYS-Llama-3.1-8B-Instruct-i1-GGUF

Quantization vs dnhkng/RYS-Llama-3.1-8B-Instruct. mradermacher/RYS-Llama-3.1-8B-Instruct-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 71 tensors match exactly and 247 within quantization error.

Tensors changed: Norms 0/71, MLP 0/105, Attention 0/140, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse