TeichAI/gpt-oss-20b-glm-4.6-distill-GGUF
LoRA-style vs armand0e/gpt-oss-20b-glm-4.6-distill. TeichAI/gpt-oss-20b-glm-4.6-distill-GGUF is a GGUF (F16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/49, MLP 0/48, Attention 96/192, lm_head 0/1, Embeddings 0/1