mradermacher/cantonese_llm_v2_chat_nemo_GRPO_Qwen3-30B-A3B-Think-2507-GGUF
Quantization vs hon9kon9ize/CantoneseLLM-v2.0-30B-A3B-Thinking. mradermacher/cantonese_llm_v2_chat_nemo_GRPO_Qwen3-30B-A3B-Think-2507-GGUF is a GGUF quantization (Q8_0) of the same weights: 241 tensors match exactly and 194 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/193, MLP 0/48, Attention 0/192, lm_head 0/1