WithinUsAI/IBM-Grok4-Ultra.Fast.Coder-1B-GGUF

Same weights, converted vs WithinUsAI/IBM-Grok4-Ultra.Fast.Coder-1B. Same weights stored in another dtype (BF16 → F16/F32), plus 120 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/81, Attention 0/160

On the Hub · Downloads on Model Pulse