mradermacher/Qwen3.5-0.8B-GPT-6-Astra-Luna-Fable-5.1-Opus-5.5-distill-Karpy-GGUF
Same weights, converted vs NasledieLab/Qwen3.5-0.8B-GPT-6-Astra-Luna-Fable-5.1-Opus-5.5-distill-Karpy. Same weights stored in another dtype (F16 → F16/F32), plus 18 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24