feat(moe): Nemotron 3.5 (nemotron_h_moe) and Ornith 1.5 support (#203)

nemotron_h_moe is the third expert layout: gate-less. Each expert is
up, ReLU^2, down, so the registry row names ffn_up_exps and
ffn_down_exps and leaves the tail slot empty, as the fused gemma4 row
does. The Mamba2/attention blocks, the shared expert, the optional
latent projections and the MTP block all stay on the resident side of
the seam. No llama.cpp change and no submodule bump: the pinned tree
already builds nemotron_h_moe.

make-tiny-moe.py learns the whole shape in miniature (hybrid stack,
latent projections, biased sigmoid router, shared expert, a trailing
MTP block that is never loaded), and it runs as a third byte-identity
gate. Every identity gate passes on it.

The architecture never puts two MoE blocks next to each other, so the
forward predictors (predict-prefetch, route-ahead, the stale half of
predict-log) have no next layer to target. The gate reads that from the
file and reports those checks N/A instead of failing or passing them
vacuously; an unreadable file keeps them strict.

Ornith-1.5-35B-A3B is qwen35moe and needs no engine change. Both models
join the Android catalog at Q4_K_M; neither has device numbers yet.

Also releases 0.25.0: versionCode 40, versionName 0.25.0, dated changelog.

examples/android/README.md

@@ -65,7 +65,10 @@ check). Nothing below needs a storage permission except the last option.
 1. **Built-in catalog** (both flavors) — the "Get a model" card offers the models this engine
    is measured on, each a single tap: **Qwen3-30B-A3B-Q4_K_M** (~18.6 GB, the reference model),
    **Qwen3.6-35B-A3B-Q4_K_M** (~22.3 GB, a hybrid attention/SSM MoE, comfortably past device RAM)
-   and **Gemma-4-26B-A4B-it-Q4_K_M** (~17 GB). Downloads run in a foreground worker, survive the
+   and **Gemma-4-26B-A4B-it-Q4_K_M** (~17 GB). Two newer entries stream through the same path
+   but have no device numbers yet: **Ornith-1.5-35B-A3B-Q4_K_M** (~21.9 GB, the Qwen3.5 MoE
+   architecture) and **Nemotron-3.5-Lightning-30B-A3B-Q4_K_M** (~25.5 GB, a hybrid
+   Mamba2/attention MoE with gate-less experts). Downloads run in a foreground worker, survive the
    app being killed, resume an interrupted transfer instead of restarting, and appear in the
    picker when done.
 2. **Any other model** — under **Other model**, paste a direct gguf URL (e.g. a Hugging Face

examples/android/app/build.gradle

@@ -51,8 +51,8 @@ android {
         applicationId 'io.bigmoeonedge.example'
         minSdk 29
         targetSdk 34
-        versionCode 39
-        versionName '0.24.0'
+        versionCode 40
+        versionName '0.25.0'
         buildConfigField 'String', 'GIT_SHA', "\"${gitSha}\""
         ndk {
             // The engine ships as prebuilt arm64 binaries staged by build-android.ps1.

examples/android/app/src/main/java/io/bigmoeonedge/example/ModelCatalog.kt

@@ -91,6 +91,24 @@ object ModelCatalog {
                 "Qwen_Qwen3.6-35B-A3B-Q4_K_M.gguf?download=true",
             blurb = "3B active of 35B. Hybrid attention/SSM, comfortably past RAM.",
         ),
+        Entry(
+            title = "Ornith-1.5-35B-A3B",
+            quant = "Q4_K_M",
+            fileName = "Ornith-1.5-35B-A3B-Q4_K_M.gguf",
+            approxBytes = 21_864_081_056L,
+            url = "https://huggingface.co/bartowski/Ornith-1.5-35B-A3B-GGUF/resolve/main/" +
+                "Ornith-1.5-35B-A3B-Q4_K_M.gguf?download=true",
+            blurb = "3B active of 35B. Qwen3.5 MoE tuned for coding and agents.",
+        ),
+        Entry(
+            title = "Nemotron-3.5-Lightning-30B-A3B",
+            quant = "Q4_K_M",
+            fileName = "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_K_M.gguf",
+            approxBytes = 25_477_403_616L,
+            url = "https://huggingface.co/bartowski/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF/resolve/main/" +
+                "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_K_M.gguf?download=true",
+            blurb = "3B active of 30B. Hybrid Mamba2/attention, gate-less experts.",
+        ),
         Entry(
             title = "Gemma-4-26B-A4B-it",
             quant = "Q4_K_M",