Lamapi/next-4b-Q4_K_M-GGUF

Quantization (fewer layers) vs thelamapi/next-4b. Lamapi/next-4b-Q4_K_M-GGUF matches part of thelamapi/next-4b (444 of its 883 tensors; the rest of thelamapi/next-4b has no counterpart). On the shared part: Lamapi/next-4b-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 205 tensors match exactly and 239 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse