mradermacher/S1-VL-32B-GGUF

Quantization (fewer layers) vs ScienceOne-AI/S1-VL-32B. mradermacher/S1-VL-32B-GGUF matches part of ScienceOne-AI/S1-VL-32B (707 of its 1058 tensors; the rest of ScienceOne-AI/S1-VL-32B has no counterpart). On the shared part: mradermacher/S1-VL-32B-GGUF is a GGUF quantization (Q8_0) of the same weights: 257 tensors match exactly and 450 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/257, MLP 0/192, Attention 0/256, lm_head 0/1

On the Hub · Downloads on Model Pulse