UraionLabs/Uraion-Agent-Small
Partial fine-tune vs Qwen/Qwen3.5-2B. UraionLabs/Uraion-Agent-Small is a GGUF (F16) of different weights. Partial change: 66% of the weights changed (attention, mlp, norms), in 24 of 24 layers.
Tensors changed: Embeddings 0/1, Norms 44/61, MLP 72/72, Attention 24/24