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.
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
'abliterated' in name/tags
is_gguf=0 (base model)
no specific method indicators - defaulting to M1 (most common)
[update:] A later 14-prompt evaluation found this v3 label-colored checkpoint underperforms the earlier v2 regex abliteration. The label-colored direction blends the regex refusal direction with an orthogonal "soft-disclaimer" component, which leaves a residual "I cannot... however..." opener on some prompts; the v2 regex direction removed those openers cleanly. Prefer v2 for refusal removal — v3 is retained for research / provenance only.
Direct-weight abliteration of zai-org/GLM-5.1-FP8 (GLM-5.1, MoE / FP8 block-quantized). This is the v3 label-colored variant: a label-colored residual refusal direction is subtracted in-place from the FP8 weights of transformer layers 13-77 (no LoRA / adapter — the surgery is baked into the weights). Method: direct_weight_surgery_fp8_block_quant.
Research artifact. Provided for safety / interpretability research on refusal direction geometry. No alignment guarantees.
The label-colored residual direction bundle used for the surgery is included at abliteration/label_colored_residual_directions.pt.
Loading
Loads as a standard GLM-5.1-FP8 checkpoint (same architecture/config as the base). Use the same runtime you would use for zai-org/GLM-5.1-FP8 (e.g. vLLM / SGLang with FP8 MoE support, or transformers with CPU offload).
README history
2 versions
The author's README evolved over time. Click a version to see its content at that point.
2026-06-15Add files using upload-large-folder tool9ac53c72 KB
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.