mradermacher/SAGE-MM-Qwen3-VL-8B-SFT_RL-i1-GGUF
Quantization (fewer layers) vs allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL. mradermacher/SAGE-MM-Qwen3-VL-8B-SFT_RL-i1-GGUF matches part of allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL (399 of its 750 tensors; the rest of allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL has no counterpart). On the shared part: mradermacher/SAGE-MM-Qwen3-VL-8B-SFT_RL-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/145, Attention 0/144, MLP 0/108, lm_head 0/1