For privacy reasons a browser tells us at most
"≥ 8 GB RAM, 8 cores" - same reading whether you have 8 GB
or 128 GB. It has no idea how much RAM is free right now, which
apps are open, or whether you have a GPU.
The Abliteration app is integrated with your machine
It reads your exact RAM, GPU model and VRAM,
free memory right now, and picks the sharpest quant that
still fits. Every model page lights up precisely for your rig.
And you can chat with any model, right now
The app is a full local runtime - no API keys, no subscription,
everything runs on your machine. Click any model on this site and
start a conversation in seconds.
Verified ARM64 Docker runtime for the AI Pod Qwen 3.8 Flash Next uncensored LPK on Thor T5000. This archive contains no model weights. It preserves the validated vLLM, FlashInfer 0.6.18, native libraries and startup caches.
Model weights are downloaded separately from pinned Hugging Face or ModelScope snapshots and mounted read-only at /model. Verify the archive size and SHA256 before docker load, then verify its Docker image ID. See checksums.json. Third-party license notices remain in the runtime.
README history
1 version
The author's README evolved over time. Click a version to see its content at that point.
2026-10-02Migrate verified inference-only runtime to dedicated repository883ffe9610 B
Loading...
Catalog is the map. Apps are the tools.
Run models on your own machine, not in the cloud.
Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.