mradermacher/Qwen3.5-0.8B-Japanese-SFT-v2-GGUF

Same weights, converted vs Takenoko12345678/Qwen3.5-0.8B-Japanese-SFT-v2. Same weights stored in another dtype (BF16 → 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