Popular repositories Loading
-
Qwen-3.8-27B-RTX-4090-3090-llama-cpp
Qwen-3.8-27B-RTX-4090-3090-llama-cpp PublicWindows llama.cpp recipe for Qwen3.8-27B on 24 GiB RTX 4090 and RTX 3090 GPUs.
PowerShell
-
Qwen-3.8-27B-RTX-5090-llama-cpp
Qwen-3.8-27B-RTX-5090-llama-cpp PublicWindows llama.cpp recipe for Qwen3.8-27B on a 32 GiB RTX 5090.
PowerShell
-
Qwen-3.8-27B-RTX-5090-SGLang
Qwen-3.8-27B-RTX-5090-SGLang PublicSGLang recipe + llama-benchy prefill/decode ladder for Qwen3.8-27B NVFP4 on RTX 5090
PowerShell
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.