lmstudio-community/pixtral-12b-GGUF
Quantization (fewer layers) vs mistral-experimental/pixtral-12b. lmstudio-community/pixtral-12b-GGUF matches part of mistral-experimental/pixtral-12b (363 of its 585 tensors; the rest of mistral-experimental/pixtral-12b has no counterpart). On the shared part: lmstudio-community/pixtral-12b-GGUF is a GGUF quantization (Q8_0) of the same weights: 81 tensors match exactly and 282 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1