OxW

Vikhr-Nemo-12B-Instruct-R-21-09-24

[GGUF] Vikhr-Nemo - это флагманская унимодальная LLM модель команды VikhrModels на базе Mistral-Nemo-Instruct-2407

382 Pulls 3 Tags Updated 5 months ago

[GGUF] Модель на базе YandexGPT-5-Lite-8B-pretrain от IlyaGusev

338 Pulls 3 Tags Updated 5 months ago

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

335 Pulls 1 Tag Updated 4 months ago

[GGUF] Saiga/Gemma3 12B, fine-tune of Gemma3 12B

193 Pulls 3 Tags Updated 4 months ago

[GGUF] Qwen2.5 instruction-tuned language model ranging from 0.5 to 72 billion parameters.

133 Pulls 1 Tag Updated 4 months ago

[GGUF/Q6_K] Finetune версия Qwen3, адаптированная для генерации русского текста.

86 Pulls 1 Tag Updated 4 months ago