mradermacher/NEW-Fuse-DeepSeek-R1-32B-ALL-GGUF

Quantization vs radna/NEW-Fuse-DeepSeek-R1-32B-ALL. mradermacher/NEW-Fuse-DeepSeek-R1-32B-ALL-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