mradermacher/STELLA-VLM-32b-i1-GGUF
Quantization (fewer layers) vs Zaixi/STELLA-VLM-32b. mradermacher/STELLA-VLM-32b-i1-GGUF matches part of Zaixi/STELLA-VLM-32b (771 of its 1161 tensors; the rest of Zaixi/STELLA-VLM-32b has no counterpart). On the shared part: mradermacher/STELLA-VLM-32b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 321 tensors match exactly and 450 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448, lm_head 0/1