yandex/YandexGPT-5-Lite-8B-instruct download history
yandex/YandexGPT-5-Lite-8B-instruct is an 8.0B-parameter model model by yandex. In the last 30 days it was downloaded 14,350 times (909 in the last 7 days), and 213,047 times in total.
It ranks #6,827 on the Hub by monthly downloads.
It has 119 likes.
It is a fine-tune of yandex/YandexGPT-5-Lite-8B-pretrain.
36 models build on YandexGPT-5-Lite-8B-instruct: 23 quantized, 3 fine-tuned, 10 adapters and 0 merges. Together with the original they were downloaded 17,293 times in the last 30 days. See the YandexGPT-5-Lite-8B-instruct galaxy.
Most downloaded derivatives
- mradermacher/YandexGPT-5-Lite-8B-instruct-i1-GGUF (quantized), 810 downloads in 30 days
- mradermacher/YandexGPT-5-Lite-8B-instruct-GGUF (quantized), 532 downloads in 30 days
- LevLv/YandexGPT-5-Lite-8B-Thinking.gguf (quantized), 399 downloads in 30 days
- dariprim/yandexgpt-5-lite-finetuned-gguf (adapter), 205 downloads in 30 days
- mlx-community/YandexGPTQ6 (quantized), 98 downloads in 30 days
- mlx-community/YandexGPT-5-Lite-8B-instruct-q2 (quantized), 89 downloads in 30 days
- mlx-community/YandexGPT-5-Lite-8B-instruct-4bit (quantized), 84 downloads in 30 days
- Theta-Lev/YandexGPT-5-Lite-8B-instruct-Q5_K_M-GGUF (quantized), 78 downloads in 30 days
- itlwas/YandexGPT-5-Lite-8B-instruct-Q4_K_M-GGUF (quantized), 74 downloads in 30 days
- deepsweet/YandexGPT-5-Lite-8B-Instruct-MLX-MXFP4 (quantized), 71 downloads in 30 days
- NikolayKozloff/YandexGPT-5-Lite-8B-instruct-Q8_0-GGUF (quantized), 58 downloads in 30 days
- deepsweet/YandexGPT-5-Lite-8B-Instruct-MLX-MXFP8 (quantized), 44 downloads in 30 days