TirGun/Sber_Qwen3-VL-2B-Instruct-action-GGUF
Quantization (fewer layers) vs SberRoboticsCenter/Qwen3-VL-2B-Instruct-action. TirGun/Sber_Qwen3-VL-2B-Instruct-action-GGUF matches part of SberRoboticsCenter/Qwen3-VL-2B-Instruct-action (310 of its 625 tensors; the rest of SberRoboticsCenter/Qwen3-VL-2B-Instruct-action has no counterpart). On the shared part: TirGun/Sber_Qwen3-VL-2B-Instruct-action-GGUF is a GGUF quantization (Q8_0) of the same weights: 113 tensors match exactly and 197 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112