jkim96/granite-4.1-8b-DASHQ-Q2-GGUF

Quantization vs ibm-granite/granite-4.1-8b. jkim96/granite-4.1-8b-DASHQ-Q2-GGUF is a GGUF quantization (IQ2_XS) of the same weights: 81 tensors match exactly and 282 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160

On the Hub · Downloads on Model Pulse