open-thoughts/OpenThinker2-32B download history
open-thoughts/OpenThinker2-32B is a 32.8B-parameter text generation model by open-thoughts. In the last 30 days it was downloaded 61 times (11 in the last 7 days), and 22,362 times in total.
It ranks #234,551 on the Hub by monthly downloads and #62,308 among text generation models.
It has 56 likes.
It is a fine-tune of Qwen/Qwen2.5-32B-Instruct.
30 models build on OpenThinker2-32B: 23 quantized, 1 fine-tuned, 2 adapters and 4 merges. Together with the original they were downloaded 7,778 times in the last 30 days. See the OpenThinker2-32B galaxy.
Most downloaded derivatives
- bartowski/open-thoughts_OpenThinker2-32B-GGUF (quantized), 2.8K downloads in 30 days
- mradermacher/OpenThinker2-32B-i1-GGUF (quantized), 947 downloads in 30 days
- mradermacher/OpenThinker2-32B-GGUF (quantized), 256 downloads in 30 days
- DevQuasar-12/open-thoughts.OpenThinker2-32B-GGUF (quantized), 178 downloads in 30 days
- lmstudio-community/OpenThinker2-32B-GGUF (quantized), 134 downloads in 30 days
- JohnRoger/OpenThinker2-32B-Q4_K_M-GGUF (quantized), 35 downloads in 30 days
- alexgusevski/OpenThinker2-32B-mlx-6Bit (quantized), 17 downloads in 30 days
- YOYO-AI/Qwen2.5-32B-YOYO-reasoning-v3 (merge), 15 downloads in 30 days
- InfinitPLEX/OpenThinker2-32B-Q3_K_S-GGUF (quantized), 14 downloads in 30 days
- uisikdag/OpenThinker2-32B-Q4_K_M-GGUF (quantized), 14 downloads in 30 days
- marcuscedricridia/Springer1.2-32B-1 (merge), 13 downloads in 30 days
- InfinitPLEX/OpenThinker2-32B-Q2_K-GGUF (quantized), 10 downloads in 30 days