Qwen3 8 27B NVFP4 DGX SPARK V2AI on my own machineModelQwen3.8-27B-NVFP4-DGX-SPARK-V2Text generation model, used with vllm.vllmqwen3_5nvfp431470kapache-2.03 wk agoAautotrustShare or keepTake it
qwen3 5 tritonAI on my own machineRepoqwen3.5-tritonPure Triton kernels for Qwen3.5-27B inference on NVIDIA B200b200cudainference125PythonMIT9 mo agoRightNow-AIShare or keepTake it
GLM 5 3 Flash NVFP4 B200 hybridAI on my own machineModelGLM-5.3-Flash-NVFP4-B200-hybridText generation model, used with safetensors.glm5_nextnvfp4fp41585mit11 d agoAAvifeneshShare or keepTake it