mradermacher/openbuddy-deepseek-67b-v15.3-4k-GGUF

Quantization vs ff670/openbuddy-deepseek-67b-v15.3-4k. mradermacher/openbuddy-deepseek-67b-v15.3-4k-GGUF is a GGUF quantization (Q5_K_M) of the same weights: 191 tensors match exactly and 667 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/191, MLP 0/285, Attention 0/380, lm_head 0/1

On the Hub · Downloads on Model Pulse