mradermacher/deepseek-v3-4layer-GGUF

Quantization vs yufanhuangNV/deepseek-v3-4layer. mradermacher/deepseek-v3-4layer-GGUF is a GGUF quantization (Q8_0) of the same weights: 18 tensors match exactly and 30 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/17, MLP 0/13, Attention 0/16, lm_head 0/1

On the Hub · Downloads on Model Pulse