Checking files on HuggingFace…
⚠ This model requires licence acceptance on HuggingFace
1 Open the model on HuggingFace in a new tab Open on HuggingFace → 2 Accept the licence (one click on their page). Stay logged in. 3 Come back and confirm I ACCEPTED → show quants
This model has no GGUF files in its repository, so the desktop
app can't run it. Abliteration accepts GGUF only — safetensors,
awq and exl2 are not supported.
View on HuggingFace →
Pick a quantization. The ★ recommended row is the biggest file that still fits your free RAM, so the best quality your hardware can run. Smaller files download faster and use less memory; bigger ones answer sharper.
HuggingFace keeps the file list private for gated repos — your acceptance only applies in your HF session, not from our server. Open the files on HuggingFace directly; the download works as soon as you're signed in there.
View files on HuggingFace →
Could not reach HuggingFace.
Retry