Hcompany/Holo-3.1-9B
Different architecture vs Qwen/Qwen3.5-0.8B. Different architecture: only 30 of 488/760 tensors match by name and shape.
5 derivatives checked
- mradermacher/Holo-3.1-9B-GGUF: Same weights, converted
- prithivMLmods/Holo-3.1-9B-GGUF: Same weights, converted
- mradermacher/Holo-3.1-9B-i1-GGUF: Quantization
- josephmayo/Holo-3.1-9B-Coder: LoRA-style (fewer layers)
- usermma/Holo-3.1-9B-abliterated-rdo: Partial fine-tune (fewer layers)
1 other repos hold byte-for-byte identical weight files.