docs: -win variant + side-load DSO + target model families

README.md

@@ -32,16 +32,39 @@ under [`releases/`](./releases) and are mirrored on the corresponding
 GitHub release at
 [mann1x/opencoti](https://github.com/mann1x/opencoti/releases).
 
+## Supported / target model families
+
+This engine is **not model-agnostic in what it optimizes**. Upstream
+llama.cpp GGUF support is unchanged (any GGUF that loads upstream
+loads here), but the opencoti feature set is built, tuned, and
+validated on two families:
+
+| Family | Role | Models | What's tuned for them |
+|---|---|---|---|
+| **Gemma-4** | **PRIMARY target** | 26B-A4B-128e MoE ("A4B"), dense 12B / 31B, elastic E-series (E2B/E4B) | head_dim 256/512 kernels, iSWA dual-cache (rolling-KV, SharedKVPool, DCA wiring), MTP via [gemma4-assistant drafters](https://huggingface.co/ManniX-ITA), fused MoE |
+| **Qwen** | SECONDARY / verification | Qwen3.5 / 3.6 dense + MoE + hybrid (gated-delta-net), Qwen2.5-14B-1M | head_dim 128 kernels, NextN self-spec MTP (fused multi-step draft), DCA long-context on 1M-class models |
+
+Other architectures run with upstream behavior; opencoti features
+either fall back safely or are unvalidated on them — see the
+model-families section at the top of [USAGE.md](./USAGE.md) before
+relying on an opencoti feature elsewhere.
+
 ## Artifacts
 
 | Artifact | Platform | GPU |
 |---|---|---|
-| `opencoti-llamafile-<ver>-<tag>-x86_64.llamafile` | x86_64 + aarch64 (fat APE; Linux/macOS/Windows/BSD) | CUDA 13.2, x86_64-linux (sm_75/80/86/89/90/120f) |
+| `opencoti-llamafile-<ver>-<tag>-x86_64.llamafile` | x86_64 + aarch64 (fat APE; Linux/macOS/BSD) | CUDA 13.2 **embedded**, x86_64-linux (sm_75/80/86/89/90/120f) |
+| `opencoti-llamafile-<ver>-<tag>-win-x86_64.llamafile.exe` | same fat APE, incl. **Windows** | none embedded — CPU out of the box, GPU via side-load (below) |
+| `dso/<ver>-<tag>/ggml-cuda-x86_64.so` | side-load DSO for the `-win`/bare APE on x86_64-linux | CUDA 13.2, x86_64-linux (sm_75/80/86/89/90/120f) |
 | `opencoti-llamafile-<ver>-<tag>-aarch64.llamafile` *(planned)* | same fat APE | CUDA 13.2, sbsa/aarch64 (sm_110f Jetson Thor, sm_121a DGX Spark GB10) |
 
-The APE host binary runs natively on both x86_64 and aarch64; the two
-artifacts differ only in the embedded `ggml-cuda.so`. On a platform
-with no matching DSO, inference falls back to CPU.
+The APE host binary is identical across variants and runs natively on
+both x86_64 and aarch64. The variants differ ONLY in the embedded
+`ggml-cuda.so`: the full x86_64 artifact carries it inside (4.8 GB);
+the `-win` variant carries none, because **Windows refuses to run
+executables larger than 4 GB** — it is the same APE renamed `.exe`
+(required on Windows) at ~55 MB. With no matching DSO available,
+inference falls back to CPU.
 
 ## Usage
 
@@ -58,6 +81,24 @@ On the first GPU run the embedded CUDA DSO self-extracts to
 string; `GET /props` exposes an `opencoti` introspection section at
 runtime (see USAGE.md §introspection).
 
+### `-win` variant / GPU side-load
+
+- **Windows:** run `opencoti-llamafile-<ver>-<tag>-win-x86_64.llamafile.exe`
+  directly (CPU inference works out of the box). For GPU, install the
+  NVIDIA CUDA Toolkit + MSVC; on first `-ngl` run llamafile compiles a
+  native `ggml-cuda.dll` on the fly into `%USERPROFILE%\.llamafile\`.
+- **Linux x86_64 (bare APE + GPU without the 4.8 GB download’s
+  re-download):** drop the published side-load DSO where the engine
+  looks before extracting an embedded one:
+
+  ```bash
+  mkdir -p ~/.llamafile/v/<ver>/   # e.g. 0.10.3
+  cp ggml-cuda-x86_64.so ~/.llamafile/v/<ver>/ggml-cuda.so
+  ```
+
+  Verify against `releases/<tag>/SHA256SUMS` first. The `-win` file is
+  still a normal APE — `sh ./…​.exe` runs fine on Linux/macOS/BSD.
+
 ## Verification
 
 Each artifact ships with a `MANIFEST.json` recording the artifact