mradermacher/Qwen2.5-Coder-32B-Instruct-abliterated-Rombo-TIES-v1.0-GGUF

Quantization vs BenevolenceMessiah/Qwen2.5-Coder-32B-Instruct-abliterated-Rombo-TIES-v1.0. mradermacher/Qwen2.5-Coder-32B-Instruct-abliterated-Rombo-TIES-v1.0-GGUF is a GGUF quantization (Q8_0) of the same weights: 321 tensors match exactly and 450 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448

On the Hub · Downloads on Model Pulse