enacimie/UI-TARS-2B-SFT-Q4_K_M-GGUF
Quantization (fewer layers) vs ByteDance-Seed/UI-TARS-2B-SFT. enacimie/UI-TARS-2B-SFT-Q4_K_M-GGUF matches part of ByteDance-Seed/UI-TARS-2B-SFT (339 of its 730 tensors; the rest of ByteDance-Seed/UI-TARS-2B-SFT has no counterpart). On the shared part: enacimie/UI-TARS-2B-SFT-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 141 tensors match exactly and 198 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1