jakeatx/Qwen3.8-Perian-BF16
LoRA-style vs jakeatx/slimder-qwen38-ream288-depth32-agentic. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/124, other 0/5, Attention 104/328, MLP 96/320