usermma/VibeThinker-3B-GGUF

Same weights, converted vs WeiboAI/VibeThinker-3B. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252

On the Hub · Downloads on Model Pulse