mradermacher/Qwen3-30B-A3B-Thinking-2507-Art-GGUF

Quantization vs taki555/Qwen3-30B-A3B-Thinking-2507-Art. mradermacher/Qwen3-30B-A3B-Thinking-2507-Art-GGUF is a GGUF quantization (Q8_0) of the same weights: 241 tensors match exactly and 194 within quantization error.

Tensors changed: Attention 0/192, Norms 0/193, MLP 0/48, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse