license: apache-2.0
base_model: huihui-ai/Huihui-Qwen3-8B-abliterated-v2
pipeline_tag: text-generation
tags:
- litertlm
- litert
- litert-lm
- android
- on-device
- edge-ai
- llm
library_name: litert-lm
Huihui-Qwen3-8B-abliterated-v2 — LiteRT-LM bundle (on-device)
Huihui-Qwen3-8B-abliterated-v2_int4_v2.litertlm — huihui-ai/Huihui-Qwen3-8B-abliterated-v2 converted to Google's
LiteRT-LM format for fully on-device inference. No cloud, no account:
the model runs entirely on the phone.
Uncensored/abliterated finetune by huihui-ai — fewer refusals than the base instruct model.
Run it
Zero code: install Local AI (free, Google Play) —
this model is in its built-in catalog. Download, tap, chat fully offline.
In your own app: the com.google.ai.edge.litertlm SDK loads this file
directly — point Engine/Conversation at it. Runtime:
https://github.com/google-ai-edge/LiteRT-LM · conversion recipes:
hf-to-litertlm.
Details
| Base model | huihui-ai/Huihui-Qwen3-8B-abliterated-v2 |
| Format | .litertlm — LiteRT-LM runtime |
| Quantization | int4 block-quantized |
| File size | 5.18 GB |
| Modality | text → text |
| License | apache-2.0 — same as the base model |
The file is byte-identical to the copy ingeladons/local-ai-models, which stays live for backward
compatibility. Per-model repos exist so each bundle has its own card, docs
and download stats.