models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen3.6-27B-W8A16-Ascend310PQwen3.8-Flash-Next-BF16-ascend-FlagOSMiniMax-M3-ascend-FlagOSAtria-Dawn-Preview-Ascend-w8a8KernelGen-LM-MoE-30BGLM-5.3-Flash-BF16-ascend-FlagOSKernelGen-LM-32B-RLKernelGen-LM-4BKernelGen-LM-1.7BXing4.0-29B-A4B-BF16-ascend-FlagOSKernelGen-LM-14BHy4-preview-INT8-ascend-FlagOSQwen-Image-2.1-BF16-ascend-FlagOSKernelGen-LM-32BQwen3.8-27B-BF16-ascend-FlagOSMoonlight-16B-A3B-ascend-FlagOSERNIE-4.5-0.3B-PT-ascend-FlagOSPhi-3.5-MoE-instruct-ascend-FlagOSminimind3-ascend-moeminimind3-ascend-denseAI21-Jamba-1.5-Mini-ascend-FlagOSQwen3.8-2.4T-A95B-INT8-ascend-FlagOSGLM-4-32B-Base-0414-ascend-FlagOSMiniCPM5-1B-ascend-FlagOSDeepSeek-R1-Distill-Qwen-1.5B-ascend-FlagOSMiniCPM5-2B-BF16-ascend-FlagOSERNIE-4.5-21B-A3B-PT-ascend-FlagOSMeta-Llama-3-8B-Instruct-ascend-FlagOSsmallq-flash-attention-ascendQwen3.8-27B-w8a8sc-Ascend310P
