mradermacher/japanese-llama-3-8b-instruct-v2-i1-GGUF

Quantization vs owner203/japanese-llama-3-8b-instruct-v2. mradermacher/japanese-llama-3-8b-instruct-v2-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 65 tensors match exactly and 226 within quantization error.

Tensors changed: Norms 0/65, MLP 0/96, Attention 0/128, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse