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++
gyro_setup.sh: set up the venv first and build with its cmake/ninja (distro cmake can be < 3.24)
Laurent Zuijdwijke05565e22301
diff --git a/tools/gyro_setup.sh b/tools/gyro_setup.shindex 11a3d9108..2d3899e9f 100755--- a/tools/gyro_setup.sh+++ b/tools/gyro_setup.sh@@ -14,7 +14,12 @@ while [ $# -gt 0 ]; do case "$1" incase "$MODEL" in S) F=Qwen3.8-Flash-Next-Gyro-S-TQ1_0.gguf; P=gyro-s;; M) F=Qwen3.8-Flash-Next-Gyro-M-TQ2_0.gguf; P=gyro-m;;*) echo "--model must be S or M"; exit 2;; esacstep() { printf '\n== %s\n' "$*"; }-for t in git cmake ninja python3; do command -v $t >/dev/null || { echo "missing: $t"; exit 1; }; done+for t in git python3; do command -v $t >/dev/null || { echo "missing: $t"; exit 1; }; done++step "python environment (also provides cmake >= 3.24 and ninja)"+[ -x .venv/bin/python ] || python3 -m venv .venv+.venv/bin/pip install -q -r requirements.txt huggingface_hub hf_transfer+export PATH="$PWD/.venv/bin:$PATH"step "agentionai llama.cpp fork (GGML with the trellis types) -> $LLAMA"[ -d "$LLAMA/ggml" ] || git clone --depth 1 https://github.com/agentionai/llama.cpp "$LLAMA"@@ -34,10 +39,6 @@ elif [ "$BACKEND" = hip ]; thenelse echo "--backend must be cuda or hip"; exit 2; ficmake --build build -j-step "python environment"-[ -x .venv/bin/python ] || python3 -m venv .venv-.venv/bin/pip install -q -r requirements.txt huggingface_hub hf_transfer-step "download $F -> $MODELS (keep it on a fast local SSD: the n-gram table is read per token)"mkdir -p "$MODELS"if [ -s "$MODELS/$F" ]; then echo "already there: $MODELS/$F (delete it to download again)"