mithulaartigala/reasoning-summarizer-qwen3.5-0.8b-preview-gguf

Same weights, converted vs mithulaartigala/reasoning-summarizer-qwen3.5-0.8b-preview. 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

On the Hub · Downloads on Model Pulse