Qwen3.5-4B-Uncensored-HauhauCS-Aggressive
by HauhauCS · built on Qwen3.5 4B · rank #71 of 135
Benchmark scores
This model is not ranked on the UGI Leaderboard yet. Estimated speed: ~12–22 tok/s (estimate), a rough range for a Q4_K_M file of this size on a recent flagship chip (Snapdragon 8 Gen 3 or A17 Pro class). It is not a measurement from this model.
About this model
Qwen3.5-4B-Uncensored-HauhauCS-Aggressive is a 4B-parameter language model by HauhauCS, derived from Qwen3.5 4B using uncensoring. You can download it and run it on your phone for free. According to its model card it refused only 0/465 prompts in the author's refusal test.
Qwen3.5-4B-Uncensored-HauhauCS-Aggressive is a 4B model by HauhauCS of Qwen3.5 4B, using uncensoring. It can look at a photo or screenshot and answer questions about it. Languages noted on the card include Chinese. The Q4_K_M file is 2.71 GB. It accepts images, so it can read a screenshot of a chart or document.
Technically, it uses the qwen35 architecture, supports a context window of 262,144 tokens (a phone will use far less), the author suggests a temperature around 0.6.
Which RAM sizes can run it?
| Device RAM | iOS-safe | Android-safe |
|---|---|---|
| 4 GB RAM | Too big | Too big |
| 6 GB RAM | Fits with Q4_K_M (~2.71 GB) | Fits with Q4_K_M (~2.71 GB) |
| 8 GB RAM | Fits with Q4_K_M (~2.71 GB) | Fits with Q4_K_M (~2.71 GB) |
| 12 GB RAM | Fits with Q4_K_M (~2.71 GB) | Fits with Q4_K_M (~2.71 GB) |
| 16 GB+ RAM | Fits with Q4_K_M (~2.71 GB) | Fits with Q4_K_M (~2.71 GB) |
iOS-safe minimum: 6 GB. Android-safe minimum: 6 GB. On iOS we treat about 57% of device RAM as usable (in the 55–60% range), because the system keeps a large share and may evict an app that goes higher. On Android we treat about 67% of device RAM as usable (in the 65–70% range), leaving room for the system and the app. See the guide.
Run it on your phone
Compatible apps:
iOS
- PocketPal AI — Free on the App Store. Can search Hugging Face and load a GGUF file on the device.
- Layla — On the App Store as a paid app. Load a custom GGUF from files on the device.
Android
- PocketPal AI — Free on Google Play. Can search Hugging Face and load a GGUF file on the device.
- Layla — On Google Play. Load a custom GGUF from storage. A limited free APK is also offered on the developer site.
- ChatterUI — Free and open source. Install the APK from the GitHub releases page. iOS is not available.
Hugging Face repository ID:
HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-AggressiveRecommended file: Q4_K_M — Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf (about 2.71 GB)
- Install one of the apps above for your operating system. PocketPal AI is free on both iOS and Android and can search Hugging Face directly.
- In the app, add a model from Hugging Face and paste this repository ID:
HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive - Download the Q4_K_M file (
Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf) (about 2.71 GB). Use wifi. This is the only step that needs internet. - Load the file and start chatting. Switch on airplane mode if you like: it keeps working. A first prompt to try:
I'm considering a decision this week. Give me the strongest case for it, the strongest case against it, and the one fact that would change my mind. Keep it short.
If the app is killed or feels slow, close other apps, try the smaller file, or pick a model with a lower iOS-safe or Android-safe minimum. On a computer, the same files work in LM Studio, Ollama and llama.cpp.
Available GGUF files (4)
| Quantization | Size | Download |
|---|---|---|
| Q4_K_MRECOMMENDED Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf | 2.71 GB | Download |
| Q6_K Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf | 3.46 GB | Download |
| Q8_0 Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf | 4.48 GB | Download |
| BF16 Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf | 8.42 GB | Download |
| Vision projector mmproj-Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf | 676 MB | Download |
Direct downloads from HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive on Hugging Face. Lower Q numbers are smaller and slightly less accurate. Vision needs the projector (mmproj) file alongside the model.