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

- 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:
2026-08-09 22:12:48 +02:00
parent b06a0349a9
commit 164bd2130a
2 changed files with 7 additions and 5 deletions

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
* 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 {
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 =
"https://huggingface.co/HauhauCS/Qwen3.5-2B-Uncensored-HauhauCS-Aggressive" +