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++
docs/INTEL_ARC.md: the CPU and model-folder paragraph in plain words
Niko1221c3326979fccc
diff --git a/docs/INTEL_ARC.md b/docs/INTEL_ARC.mdindex 531523729..1db7e3dea 100644--- a/docs/INTEL_ARC.md+++ b/docs/INTEL_ARC.md@@ -38,11 +38,11 @@ engine package. Otherwise [build the image yourself](DOCKER.md#build-it-yourself- **Linux**, for example Ubuntu 24.04, with Intel's GPU driver: the `xe` or `i915` kernel driver plus the compute runtime andLevel Zero. On Ubuntu: `intel-opencl-icd libze1 libze-intel-gpu1`, or follow Intel's[client GPU guide](https://dgpu-docs.intel.com/driver/client/overview.html).-- **The CPU and the model folder.** The CPU needs no AVX-512: a Ryzen 3000-5000 or an Intel Core 12th-14th generation runs the experts that- do not fit on the card on AVX2 (measured on an A750 with a Ryzen 5 5600X, [INTEL.md](INTEL.md)). That holds for the model folders that- have a `native_experts.txt` (IQ3_XXS, IQ3_S, NVFP4, Unsloth). The older Q2_0 folder without that file has a CPU kernel that needs- AVX-512; the engine then stops with "this CPU cannot run the expert kernel", `strata doctor` says so before the start, and- building the model folder again with `tools/iq_pack.py` (or `strata setup`) fixes it.+- **The CPU and the model folder.** The CPU does not need AVX-512. A Ryzen 3000-5000 or an Intel Core 12th-14th generation runs the+ experts that do not fit on the card with AVX2 (measured on an A750 with a Ryzen 5 5600X, [INTEL.md](INTEL.md)). This applies to+ model folders that contain `native_experts.txt` (IQ3_XXS, IQ3_S, NVFP4, Unsloth). An older Q2_0 folder has no such file, and its+ CPU kernel needs AVX-512. With that folder the engine stops with "this CPU cannot run the expert kernel", and `strata doctor`+ warns about it before the start. Building the model folder again with `strata setup` (or `tools/iq_pack.py`) fixes it.- For a source build without Docker: **Intel oneAPI** with the DPC++ compiler (`icpx`, 2025.3 or newer) and **oneMKL**(about 5 GB), `cmake` 3.24+, `ninja`, `git`, Python 3. The build fetches ggml unless you point `STRATA_GGML_DIR` at allama.cpp checkout.