juli/tsjetpiti
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Switch model to Q6_K (~1.5 GB), lighter/faster than Q8

Browse Source 
- ModelDownloader now pulls the Q6_K quant
- README: reflect Q6_K sizes + note prebuilt APK on Releases

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
juli
2026-08-09 22:12:48 +02:00
parent b06a0349a9
commit 164bd2130a
2 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -30,7 +30,7 @@ conversation and start fresh.
- **Inference:** llama.cpp compiled from source (pinned tag `b10333`) through the - **Inference:** llama.cpp compiled from source (pinned tag `b10333`) through the
NDK. Pulled automatically at build time via CMake `FetchContent` — no submodule NDK. Pulled automatically at build time via CMake `FetchContent` — no submodule
to init. to init.
- **Model:** `Qwen3.5-2B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf` (~1.9 GB) is - **Model:** `Qwen3.5-2B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf` (~1.5 GB) is
**downloaded on first launch** from Hugging Face into the app's private storage. **downloaded on first launch** from Hugging Face into the app's private storage.
It is *not* bundled in the APK. (Swap the quant in `ModelDownloader.kt`.) It is *not* bundled in the APK. (Swap the quant in `ModelDownloader.kt`.)
- **Persona:** set via `SYSTEM_PROMPT` in `MainActivity.kt`; sampling is a little - **Persona:** set via `SYSTEM_PROMPT` in `MainActivity.kt`; sampling is a little
@@ -47,7 +47,7 @@ conversation and start fresh.
in **Android Studio** (it will offer to install the matching NDK `27.2.12479018` in **Android Studio** (it will offer to install the matching NDK `27.2.12479018`
and CMake `3.22.1`). and CMake `3.22.1`).
- **A phone:** 64-bit ARM (`arm64-v8a`), Android 8.0+ (minSdk 26), and enough free - **A phone:** 64-bit ARM (`arm64-v8a`), Android 8.0+ (minSdk 26), and enough free
RAM to hold a ~1.9 GB Q8 model (~4+ GB RAM device recommended). RAM to hold a ~1.5 GB Q6 model (~4 GB RAM device recommended).
- Network on first launch to download the model. - Network on first launch to download the model.
## Build ## Build
@@ -63,9 +63,11 @@ The APK lands in `app/build/outputs/apk/debug/`. Or just Run ▶ from Android St
## Install (sideload) ## Install (sideload)
A prebuilt `app-debug.apk` is attached to every [Release](../../releases).
The debug APK is signed with the debug key, so you can sideload it directly: The debug APK is signed with the debug key, so you can sideload it directly:
copy `app-debug.apk` to the phone, enable "install unknown apps" for your file copy `app-debug.apk` to the phone, enable "install unknown apps" for your file
manager, and tap it. First launch downloads the ~1.9 GB model over Wi-Fi. manager, and tap it. First launch downloads the ~1.5 GB model over Wi-Fi.
## Where things live ## Where things live

4
app/src/main/java/monster/autisme/tsjetpiti/ModelDownloader.kt
View File

@@ -7,11 +7,11 @@ import java.net.URL
/** /**
* Downloads the GGUF model on first launch and caches it in the app's private * Downloads the GGUF model on first launch and caches it in the app's private
* files dir. ~1.9 GB (Q8_0), so it only happens once. * files dir. ~1.5 GB (Q6_K), so it only happens once.
*/ */
object ModelDownloader { object ModelDownloader {
const val MODEL_FILENAME = "Qwen3.5-2B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf" const val MODEL_FILENAME = "Qwen3.5-2B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf"
private const val MODEL_URL = private const val MODEL_URL =
"https://huggingface.co/HauhauCS/Qwen3.5-2B-Uncensored-HauhauCS-Aggressive" + "https://huggingface.co/HauhauCS/Qwen3.5-2B-Uncensored-HauhauCS-Aggressive" +