mradermacher/Qwen3-32B-108B-A32B-i1-GGUF

Quantization vs LLMcompe-Team-Watanabe/Qwen3-32B-108B-A32B. mradermacher/Qwen3-32B-108B-A32B-i1-GGUF is a GGUF quantization (IQ3_S) of the same weights: 321 tensors match exactly and 258 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/257, MLP 0/64, Attention 0/256, lm_head 0/1

On the Hub · Downloads on Model Pulse