mradermacher/RC-Qwen2VL-2b-GGUF
Same weights, converted (fewer layers) vs weihongliang/RC-Qwen2VL-2b. mradermacher/RC-Qwen2VL-2b-GGUF matches part of weihongliang/RC-Qwen2VL-2b (338 of its 729 tensors; the rest of weihongliang/RC-Qwen2VL-2b has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196