mradermacher/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-GGUF

Quantization vs YOYO-AI/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507. mradermacher/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-GGUF is a GGUF quantization (Q8_0) of the same weights: 241 tensors match exactly and 194 within quantization error.

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

On the Hub · Downloads on Model Pulse