← back to catalog · registered 2026-08-22 13:56

ayunami2000/GLM-4.7-Flash-ultimate-uncensored-heretic

ayunami2000 Glm 30B MoE
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/ayunami2000%2FGLM-4.7-Flash-ultimate-uncensored-heretic"
Response includes
  • classification m3
  • files 9
  • hub_downloads_all_time 53
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · lifetime
53
12 last 30d - stable
Likes
1
Model age
6mo ago
created 2026-03-19
Downloads over time
Now54→from12↑350%
1026425812 on Mar 1854 on Oct 1154 on Oct 8MarAprMayJunJulAugSepOct
Mar 18 → Oct 11 · 69 snapshots · spans 207 days

Metadata

Tags
safetensors glm4_moe_lite region:us
Total size
55.8 GB
Files
9
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-19 01:16

Files by quantization

Auxiliary files 9 files 55.8 GB
model-00001-of-00002.safetensors 46.3 GB a9f5117f download
model-00002-of-00002.safetensors 9.47 GB 99ae21d8 download
tokenizer.json 19.3 MB 2f2005e8 download
model.safetensors.index.json 842 KB 6346a262 download
chat_template.jinja 3.13 KB 336060dd download
config.json 2.03 KB 97c0da4d download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 316 B bbddef09 download
generation_config.json 187 B cd9039fd download

README

The author did not publish a README.

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.

Open in Abliteration