42ailab/Logics-PPT-Qwen3.6-35B-A3B-RL-GGUF
Quantization vs Logics-MLLM/Logics-PPT-Qwen3.6-35B-A3B-RL. 42ailab/Logics-PPT-Qwen3.6-35B-A3B-RL-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 141 tensors match exactly and 162 within quantization error.
Tensors changed: Norms 0/101, MLP 0/160, Attention 0/40, Embeddings 0/1, lm_head 0/1