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:
@@ -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" +
|
||||
|
||||
Reference in New Issue
Block a user