shisa-ai/Ornith-1.5-35B-A3B-MTP
Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 99% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 2/5, Attention 268/392, MLP 287/399, Norms 115/247, lm_head 1/1, other 1/1
7 derivatives checked
- mradermacher/Ornith-1.5-35B-A3B-MTP-GGUF: Quantization
- mradermacher/Ornith-1.5-35B-A3B-MTP-i1-GGUF: Quantization
- RukaRat/Ornith-1.5-35B-A3B-oQ6-gs128-mtp-vision: Quantization
- pyros-vault/Ornith-1.5-35B-A3B-oQ4e-fixed-mtp: Quantization
- jk797/Ornith-1.5-35B-A3B-oQ5e-gs128-mtp-vision: Quantization
- pyros-vault/Ornith-1.5-35B-A3B-oQ6e-fixed-mtp: Quantization
- pyros-vault/Ornith-1.5-35B-A3B-oQ8e-fixed-mtp: Quantization