thusinh1969

Dùng cho Gemma-4-31B

Dùng cho Qwen3-Omni-31B-A3B

For Qwen3-ASR

Dùng cho Qwen3-80B-Dense

EraX Rerank LLM with 4096 context length

EraX Embedding model with 4096 context length

NVIDIA CUDA 11.6/CUDNN8, Pytorch 1.13.1 to run Stable Diffusions with Automatic111 WebUI.