SandLogicTechnologies/deepseek-coder-1.3b-instruct-GGUF

Quantization vs deepseek-ai/deepseek-coder-1.3b-instruct. SandLogicTechnologies/deepseek-coder-1.3b-instruct-GGUF is a GGUF quantization (IQ4_XS) of the same weights: 49 tensors match exactly and 170 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96

On the Hub · Downloads on Model Pulse