kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF
Quantization (fewer layers) vs microsoft/Phi-4-reasoning-vision-15B. kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF matches part of microsoft/Phi-4-reasoning-vision-15B (243 of its 695 tensors; the rest of microsoft/Phi-4-reasoning-vision-15B has no counterpart). On the shared part: kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF is a GGUF quantization (Q8_0_ROCMFPX) of the same weights: 81 tensors match exactly and 2 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/81, lm_head 0/1