mradermacher/VST-3B-RL-i1-GGUF
Quantization (fewer layers) vs rayruiyang/VST-3B-RL. mradermacher/VST-3B-RL-i1-GGUF matches part of rayruiyang/VST-3B-RL (435 of its 825 tensors; the rest of rayruiyang/VST-3B-RL has no counterpart). On the shared part: mradermacher/VST-3B-RL-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 181 tensors match exactly and 254 within quantization error.
Tensors changed: lm_head 0/1, Norms 0/73, Attention 0/252, MLP 0/108, Embeddings 0/1