mradermacher/k-27b-GGUF

Quantization (fewer layers) vs ThomasTheMaker/k-27b. mradermacher/k-27b-GGUF matches part of ThomasTheMaker/k-27b (808 of its 1247 tensors; the rest of ThomasTheMaker/k-27b has no counterpart). On the shared part: mradermacher/k-27b-GGUF is a GGUF quantization (Q8_0) of the same weights: 373 tensors match exactly and 435 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/373, MLP 0/186, Attention 0/248

On the Hub · Downloads on Model Pulse