mradermacher/gpt-oss-20b-multilingual-reasoner-GGUF
Full fine-tune vs xxrjun/gpt-oss-20b-multilingual-reasoner. mradermacher/gpt-oss-20b-multilingual-reasoner-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 4/49, MLP 48/48, Attention 192/192, lm_head 1/1