QUASAR-QAT/Qwen3.5-4B-QUASAR-Q4_0-GGUF
Quantization vs Qwen/Qwen3.5-4B. QUASAR-QAT/Qwen3.5-4B-QUASAR-Q4_0-GGUF is a GGUF quantization (Q4_0/F16) of the same weights: 82 tensors match exactly and 128 within quantization error.
Tensors changed: Embeddings 0/1, MLP 0/96, Norms 0/81, Attention 0/32