mradermacher/Youtu-VL-4B-Instruct-i1-GGUF

Quantization vs tencent/Youtu-VL-4B-Instruct. mradermacher/Youtu-VL-4B-Instruct-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 161 tensors match exactly and 281 within quantization error.

Tensors changed: Norms 0/161, MLP 0/120, Attention 0/160, Embeddings 0/1

On the Hub · Downloads on Model Pulse