hon9kon9ize/CantoneseLLM-v2.0-30B-A3B-Thinking download history
hon9kon9ize/CantoneseLLM-v2.0-30B-A3B-Thinking is a 30.5B-parameter text generation model by hon9kon9ize. In the last 30 days it was downloaded 655 times (109 in the last 7 days), and 1,453 times in total.
It ranks #50,914 on the Hub by monthly downloads and #14,517 among text generation models.
It has 3 likes.
It is a fine-tune of Qwen/Qwen3-30B-A3B-Base.
3 models build on CantoneseLLM-v2.0-30B-A3B-Thinking: 3 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 3,647 times in the last 30 days. See the CantoneseLLM-v2.0-30B-A3B-Thinking galaxy.
Most downloaded derivatives
- mradermacher/cantonese_llm_v2_chat_nemo_GRPO_Qwen3-30B-A3B-Think-2507-GGUF (quantized), 1.8K downloads in 30 days
- mradermacher/CantoneseLLM-v2.0-30B-A3B-Thinking-i1-GGUF (quantized), 1K downloads in 30 days
- mradermacher/CantoneseLLM-v2.0-30B-A3B-Thinking-GGUF (quantized), 232 downloads in 30 days
Open hon9kon9ize/CantoneseLLM-v2.0-30B-A3B-Thinking on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.