aashish1904/Jan-v3-4B-base-instruct-GGUF

Quantization vs janhq/Jan-v3-4B-base-instruct. aashish1904/Jan-v3-4B-base-instruct-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 254 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/108, Norms 0/145, Attention 0/144

On the Hub · Downloads on Model Pulse