Arm/qwen3-vl-2b-instruct-q4-k-m-ggml-llama-cpp-vivo-x300
Quantization (fewer layers) vs Qwen/Qwen3-VL-2B-Instruct. Arm/qwen3-vl-2b-instruct-q4-k-m-ggml-llama-cpp-vivo-x300 matches part of Qwen/Qwen3-VL-2B-Instruct (310 of its 625 tensors; the rest of Qwen/Qwen3-VL-2B-Instruct has no counterpart). On the shared part: Arm/qwen3-vl-2b-instruct-q4-k-m-ggml-llama-cpp-vivo-x300 is a GGUF quantization (Q4_K/Q6_K) 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