license: apache-2.0
language:
- en
pipeline_tag: text-generation
base_model: Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1
tags: - mnn
- qwen3
- mobile
- on-device
- tokforge
- uncensored
- abliterated
TokForge
- Website: https://tokforge.ai
- Discord: https://discord.gg/Acv3CBtfVm
- Google Play: https://play.google.com/store/apps/details?id=dev.tokforge
- iOS TestFlight: https://testflight.apple.com/join/jnufjzRr
Runs on-device in the TokForge app.
Josiefied-Qwen3-8B-abliterated-v1-MNN
Pre-converted Josiefied-Qwen3-8B-abliterated-v1 in MNN format for on-device inference with TokForge.
Original model by Goekdeniz-Guelmez — converted to MNN Q4 for mobile deployment.
Model Details
| Architecture | Qwen3 (standard multi-head attention, 36 layers) |
| Parameters | 8B (4-bit quantized) |
| Format | MNN (Alibaba Mobile Neural Network) |
| Quantization | W4A16 (4-bit weights, block size 128) |
| Vocab | 151,936 tokens |
| Source | Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 |
Description
Josiefied abliterated v1 by Goekdeniz Guelmez — 8B Qwen3 with abliterated safety filters. Excellent quality-to-speed ratio for flagship phones. Runs comfortably on 12GB+ RAM devices with OpenCL GPU acceleration.
Files
| File | Description |
|---|---|
llm.mnn |
Model computation graph |
llm.mnn.weight |
Quantized weight data (Q4, block=128) |
llm_config.json |
Model config with Jinja chat template |
tokenizer.txt |
Tokenizer vocabulary |
config.json |
MNN runtime config |
Usage with TokForge
This model is optimized for TokForge — a free Android app for private, on-device LLM inference.
- Download TokForge from the Play Store
- Open the app → Models → Download this model
- Start chatting — runs 100% locally, no internet required
Recommended Settings
| Setting | Value |
|---|---|
| Backend | OpenCL (Qualcomm) / Vulkan (MediaTek) / CPU (fallback) |
| Precision | Low |
| Threads | 4 |
| Thinking | Off (or On for thinking-capable models) |
Speculative Decoding
Pair with the TokForge Acceleration Pack for speculative decoding. On our test devices, speculative decoding with dense Qwen3 targets measured +34% to +43% faster decode in chat workloads. Results vary by device and workload.
Performance
Actual speed varies by device, thermal state, and generation length. Typical ranges for this model size:
| Device | SoC | Backend | Approx. tok/s |
|---|---|---|---|
| SM8850 (RedMagic) | Snapdragon 8 Elite 2 | OpenCL | ~14 tok/s |
| SM8650 (Lenovo) | Snapdragon 8 Gen 3 | OpenCL | ~10 tok/s |
| D9400+ (OnePlus) | Dimensity 9400 | OpenCL | ~9 tok/s |
Attribution
This is an MNN conversion of Josiefied-Qwen3-8B-abliterated-v1 by Goekdeniz-Guelmez. All credit for the model architecture, training, and fine-tuning goes to the original author(s). This conversion only changes the runtime format for mobile deployment.
Limitations
- Intended for TokForge / MNN on-device inference on Android
- This is a runtime bundle, not a standard Transformers training checkpoint
- Quantization (Q4) may slightly reduce quality compared to the full-precision original
- Abliterated/uncensored models have had safety filters removed — use responsibly
Community
- Website: tokforge.ai
- Discord: Join our Discord
- GitHub: TokForge on GitHub
Export Details
Converted using MNN's llmexport pipeline:
python llmexport.py --path Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 --export mnn --quant_bit 4 --quant_block 128