llm-jp/llm-jp-4-32b-a3b-thinking download history
llm-jp/llm-jp-4-32b-a3b-thinking is a 32.1B-parameter text generation model by llm-jp. In the last 30 days it was downloaded 2,666 times (437 in the last 7 days), and 67,125 times in total.
It ranks #17,177 on the Hub by monthly downloads and #4,507 among text generation models.
It has 40 likes.
14 models build on llm-jp-4-32b-a3b-thinking: 10 quantized, 2 fine-tuned, 0 adapters and 2 merges. Together with the original they were downloaded 4,629 times in the last 30 days. See the llm-jp-4-32b-a3b-thinking galaxy.
Most downloaded derivatives
- mmnga-o/llm-jp-4-32b-a3b-thinking-gguf (quantized), 313 downloads in 30 days
- hiratagoh/llm-jp-4-32b-a3b-thinking-GGUF (quantized), 245 downloads in 30 days
- mlx-community/llm-jp-4-32b-a3b-thinking-8bit (quantized), 208 downloads in 30 days
- alfredplpl/llm-jp-4-32b-a3b-thinking-gguf (quantized), 130 downloads in 30 days
- mlx-community/llm-jp-4-32b-a3b-thinking-4bit (quantized), 126 downloads in 30 days
- sakamakismile/llm-jp-4-32b-a3b-thinking-NVFP4 (quantized), 107 downloads in 30 days
- ash2813/llm-jp-4-32b-a3b-thinking-gguf (quantized), 101 downloads in 30 days
- Maji001/llm-jp-4-32b-a3b-thinking-mlx-nvfp4-mixed (quantized), 95 downloads in 30 days
- third-intelligence/llm-jp-4-kappa-32b-a3b-v0.1 (finetune), 84 downloads in 30 days
- ikedachin/llm-jp-4-32b-a3b-thinking-imabari-v2 (finetune), 68 downloads in 30 days
- InfiniCloud/llm-jp-4-32b-a3b-thinking-GPTQ-INT4-G64 (quantized), 35 downloads in 30 days
- aixsatoshi/llm-jp-4-64b-a6b-merged (merge), 21 downloads in 30 days