mradermacher/Pixtral-12B-2409-StarFlow-GGUF
Quantization (fewer layers) vs ServiceNow/Pixtral-12B-2409-StarFlow. mradermacher/Pixtral-12B-2409-StarFlow-GGUF matches part of ServiceNow/Pixtral-12B-2409-StarFlow (363 of its 585 tensors; the rest of ServiceNow/Pixtral-12B-2409-StarFlow has no counterpart). On the shared part: mradermacher/Pixtral-12B-2409-StarFlow-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