TirGun/Sber_Qwen3-VL-4B-Instruct-action-GGUF

Quantization (fewer layers) vs SberRoboticsCenter/Qwen3-VL-4B-Instruct-action. TirGun/Sber_Qwen3-VL-4B-Instruct-action-GGUF matches part of SberRoboticsCenter/Qwen3-VL-4B-Instruct-action (398 of its 713 tensors; the rest of SberRoboticsCenter/Qwen3-VL-4B-Instruct-action has no counterpart). On the shared part: TirGun/Sber_Qwen3-VL-4B-Instruct-action-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 253 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144

On the Hub · Downloads on Model Pulse