mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-GGUF
Quantization vs DavidAU/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored. mradermacher/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-GGUF is a GGUF quantization (Q8_0) of the same weights: 341 tensors match exactly and 478 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/137, MLP 0/204, Attention 0/476