Tesslate/UIGEN-T3-4B-Preview
LoRA-style vs Qwen/Qwen3-4B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 108/108, Attention 144/144
5 derivatives checked
- mradermacher/UIGEN-T3-4B-Preview-i1-GGUF: Quantization
- Tesslate/UIGEN-T3-4B-Preview-GGUF: Same weights, converted
- prithivMLmods/UIGEN-T3-4B-Preview-GGUF: Same weights, converted
- mradermacher/UIGEN-T3-4B-Preview-GGUF: Same weights, converted
- prithivMLmods/Muscae-Qwen3-UI-Code-4B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.