mradermacher/ERNIE-21B-A3B-Thinking-Gemini-3-Pro-High-Reasoning-V2-GGUF
Quantization vs DavidAU/ERNIE-21B-A3B-Thinking-Gemini-3-Pro-High-Reasoning-V2. mradermacher/ERNIE-21B-A3B-Thinking-Gemini-3-Pro-High-Reasoning-V2-GGUF is a GGUF quantization (Q8_0) of the same weights: 84 tensors match exactly and 197 within quantization error.
Tensors changed: MLP 0/111, Embeddings 0/1, Norms 0/57, Attention 0/112