mradermacher/Helios-Flare-31B-GGUF
Quantization (fewer layers) vs Vortex5/Helios-Flare-31B. mradermacher/Helios-Flare-31B-GGUF matches part of Vortex5/Helios-Flare-31B (772 of its 1188 tensors; the rest of Vortex5/Helios-Flare-31B has no counterpart). On the shared part: mradermacher/Helios-Flare-31B-GGUF is a GGUF quantization (Q8_0) of the same weights: 361 tensors match exactly and 411 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230