Published by TokForge for on-device inference.
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.
Qwen3.5-4B-Claude-4.6-Opus-abliterated (MNN)
Pre-converted Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated (huihui-ai's abliteration of Jackrong's Claude 4.6 Opus reasoning distill of Qwen3.5-4B) in MNN format for on-device inference.
Model Details
- Architecture: Qwen3.5 (hybrid LinearAttention + standard attention)
- Parameters: 4B (4-bit quantized)
- Format: MNN (Alibaba Mobile Neural Network)
- Quantization: W4A16 (4-bit weights, 16-bit activations)
- Attention: LinearAttention (gated_delta_rule) + standard attention hybrid
Backend
CPU is recommended for Qwen3.5 models (LinearAttention runs natively on CPU).
Usage with TokForge
Optimized for TokForge, an Android app for on-device LLM inference.
Abliteration
Safety filters removed for unrestricted conversation. Use responsibly.
Limitations and Intended Use
- Intended for TokForge / MNN on-device inference, especially creative writing and roleplay use.
Qwen3.5hybrid LinearAttention models generally route best to CPU in current TokForge builds.- Performance varies by device class and generation length.
- This repo is a packaged runtime artifact, not a standard Transformers training checkpoint.
Credits
- Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated by huihui-ai (Hugging Face). Used under the Apache-2.0 license. Our MNN files were converted from this model.
- Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled by Jackrong (Hugging Face). Used under the Apache-2.0 license. Reasoning-distilled from Claude 4.6 Opus outputs; not an Anthropic release.
- Qwen3.5-4B by the Qwen team (Alibaba Cloud) (Hugging Face). Used under the Apache-2.0 license.
- Converted with llmexport from MNN by Alibaba (Apache-2.0).
Community
- Website: tokforge.ai
- Discord: Join the Discord