Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
dgx_smoke: the setup check is read case-insensitively (setup prints ARM64) and reports the GPU line
Niko1221b4814a9fb149
diff --git a/tools/dgx_smoke.py b/tools/dgx_smoke.pyindex 4daa83a01..a534771df 100644--- a/tools/dgx_smoke.py+++ b/tools/dgx_smoke.py@@ -32,8 +32,10 @@ def sh(cmd: str) -> tuple[int, str]:def check_setup(data_dir: str) -> tuple[bool, str]:rc, out = sh(f"{PY} setup.py --check --yes --data-dir '{data_dir}' 2>&1 | head -8")- ok = "unified memory" in out and "arm64" in out- return ok, out.strip().splitlines()[0] if out.strip() else "no output"+ low = out.lower()+ ok = "unified memory" in low and "arm64" in low+ gpu = next((line.strip() for line in out.splitlines() if "GPU:" in line), "")+ return ok, gpu or (out.strip().splitlines()[0] if out.strip() else "no output")def bench(config: str, cell: str, out_dir: str) -> dict | None: