mradermacher/IntrinSight-4B-i1-GGUF

Quantization (fewer layers) vs qiuxi337/IntrinSight-4B. mradermacher/IntrinSight-4B-i1-GGUF matches part of qiuxi337/IntrinSight-4B (445 of its 884 tensors; the rest of qiuxi337/IntrinSight-4B has no counterpart). On the shared part: mradermacher/IntrinSight-4B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 205 tensors match exactly and 240 within quantization error.

Tensors changed: Norms 0/205, MLP 0/102, Attention 0/136, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse