Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix

by DavidAU · built on Qwen3.5 9B heretic v2 · rank #95 of 135

NewUncensored9BThinkingVisionCodeMar 2026
8.7Kdownloads150likes

Benchmark scores

This model is not ranked on the UGI Leaderboard yet. Estimated speed: ~6–12 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

Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix is a 9B-parameter language model by DavidAU, derived from trohrbaugh/Qwen3.5-9B-heretic-v2 using Heretic, an automated abliteration tool. You can download it and run it on your phone for free.

Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix is a 9B model by DavidAU of Qwen3.5 9B heretic v2, using heretic, an automated abliteration tool. It can read images and writes out its reasoning before it answers, and is set up for writing code. The Q4_K_M file is 6.84 GB. It writes out its reasoning before answering, which is slower but more careful, and 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).

Which RAM sizes can run it?

Device RAMiOS-safeAndroid-safe
4 GB RAMToo bigToo big
6 GB RAMToo bigToo big
8 GB RAMToo bigToo big
12 GB RAMFits with Q4_K_M (~6.84 GB)Fits with Q4_K_M (~6.84 GB)
16 GB+ RAMFits with Q4_K_M (~6.84 GB)Fits with Q4_K_M (~6.84 GB)

iOS-safe minimum: 12 GB. Android-safe minimum: 12 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:

DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix-GGUF

Recommended file: Q4_K_M — Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-Q4_K_M-imat.gguf (about 6.84 GB)

Download Q4_K_M from Hugging Face

  1. 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.
  2. In the app, add a model from Hugging Face and paste this repository ID:
    DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix-GGUF
  3. Download the Q4_K_M file (Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-Q4_K_M-imat.gguf) (about 6.84 GB). Use wifi. This is the only step that needs internet.
  4. 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 (11)

QuantizationSizeDownload
IQ2_M
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-IQ2_M-imat.gguf
4.76 GBDownload
IQ3_M
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-IQ3_M-imat.gguf
5.63 GBDownload
IQ4_XS
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-IQ4_XS-imat.gguf
6.28 GBDownload
IQ4_NL
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-IQ4_NL-imat.gguf
6.53 GBDownload
Q4_K_S
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-Q4_K_S-imat.gguf
6.55 GBDownload
Q4_K_MRECOMMENDED
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-Q4_K_M-imat.gguf
6.84 GBDownload
Q5_K_S
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-Q5_K_S-imat.gguf
7.51 GBDownload
Q5_K_M
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-Q5_K_M-imat.gguf
7.73 GBDownload
Q6_K
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-Q6_K-imat.gguf
8.57 GBDownload
Q8_0
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-Q8_0.gguf
10.49 GBDownload
BF16
Qwen3.5-9B-Claude-4.6-OS-AV-H-UNCENSORED-THINK-D_AU-BF16.gguf
17.92 GBDownload
Vision projector
mmproj-F16.gguf
918 MBDownload
Vision projector
mmproj-BF16.gguf
922 MBDownload
Vision projector
mmproj-F32.gguf
1.82 GBDownload

Direct downloads from DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix-GGUF on Hugging Face. Lower Q numbers are smaller and slightly less accurate. Vision needs the projector (mmproj) file alongside the model.

Similar models

Copied