mradermacher/UnifiedReward-Edit-qwen3vl-32b-i1-GGUF
Quantization (fewer layers) vs CodeGoat24/UnifiedReward-Edit-qwen3vl-32b. mradermacher/UnifiedReward-Edit-qwen3vl-32b-i1-GGUF matches part of CodeGoat24/UnifiedReward-Edit-qwen3vl-32b (707 of its 1058 tensors; the rest of CodeGoat24/UnifiedReward-Edit-qwen3vl-32b has no counterpart). On the shared part: mradermacher/UnifiedReward-Edit-qwen3vl-32b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 257 tensors match exactly and 450 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/257, MLP 0/192, Attention 0/256, lm_head 0/1