---
license: apache-2.0
base_model: huihui-ai/Huihui-Qwen3-4B-abliterated-v2
tags:
- mnn
- abliterated
- uncensored
- roleplay
- spec-decode
- tokforge
---

## 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.

# Qwen3-4B Abliterated MNN

MNN 4-bit HQQ quantized model for [TokForge](https://tokforge.ai) on-device inference.

## Model Info

| | |
|---|---|
| **Parameters** | 4B |
| **Quantization** | 4-bit HQQ (quant_block=64) |
| **Size** | 2.4GB |
| **Source** | [huihui-ai/Huihui-Qwen3-4B-abliterated-v2](https://huggingface.co/huihui-ai/Huihui-Qwen3-4B-abliterated-v2) |
| **Backend** | MNN OpenCL (GPU-accelerated) |
| **Min RAM** | 8GB+ |

## Performance

Performance varies by device, backend routing, and thermal state. 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.

## Speculative Decoding

This model is compatible with the [TokForge Acceleration Pack](https://huggingface.co/darkmaniac7/TokForge-AccelerationPack-Draft) (Qwen3-0.6B draft model), which works with both censored and uncensored targets.

## Usage

Download via TokForge app → Models → Roleplay category, or manually place files in the TokForge models directory.

## Limitations and Intended Use

- Intended for TokForge / MNN mobile inference.
- `4B` was not the strongest speculative-decoding target in our later preserved fleet results.
- Performance depends strongly on SoC, backend routing, and device thermal behavior.
- This repo is a runtime/export artifact, not a standard Transformers release.

## Files

- `llm.mnn` — Model graph
- `llm.mnn.weight` — Quantized weights
- `tokenizer.txt` — Tokenizer vocabulary
- `llm_config.json` — Model configuration
- `embeddings_bf16.bin` — Embedding table (8B/14B only)

## Credits

- Original model: [huihui-ai/Huihui-Qwen3-4B-abliterated-v2](https://huggingface.co/huihui-ai/Huihui-Qwen3-4B-abliterated-v2)
- MNN framework: [alibaba/MNN](https://github.com/alibaba/MNN)
- TokForge: [tokforge.ai](https://tokforge.ai)

## Community

- Website: [tokforge.ai](https://tokforge.ai)
- Discord: [Join the Discord](https://discord.gg/Acv3CBtfVm)