Get the app
← back to catalog · registered 2026-09-10 10:55

mradermacher/Muse-Glimmer-30B-Uncensored-Heretic-i1-GGUF

mradermacher 30B GGUF 131K ctx
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/mradermacher%2FMuse-Glimmer-30B-Uncensored-Heretic-i1-GGUF"
Response includes
  • classification m3
  • files 3
  • hub_downloads_all_time 7,379
  • author_summary 3405 models
  • readme_text full
Try next
GET/models?author=mradermacher
All 3405 models by mradermacher
 GET/methods/m3
What "m3" means · taxonomy
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
M1 Direct removal →
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)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
7K
2K last 30d - stable
Likes
0
Model age
6w ago
created 2026-09-10
Downloads over time
Now9.3K→from0↑0%
03.4K6.8K10.2K0 on Sep 109.3K on Oct 26SepOct
Sep 10 → Oct 26 · 47 snapshots · spans 46 days

Variants by this author 2 formats · 5K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Tags
transformers gguf heretic uncensored decensored abliterated en base_model:OS-Software/Muse-Glimmer-30B-Uncensored-Heretic base_model:quantized:OS-Software/Muse-Glimmer-30B-Uncensored-Heretic license:apache-2.0 endpoints_compatible region:us

Related

Other by mradermacher
Ornith-1.5-9B-uncensored-GGUF 1.7M Qwen3-VL-8B-Instruct-abliterated-GGUF 653K Qwen3.8-Flash-Next-Uncensored-i1-GGUF 171K Huihui-Qwen3.5-9B-abliterated-GGUF 162K Huihui-Qwen3.8-Flash-Next-abliterated-i1-GGUF 106K
Total size
12.8 MB
Files
3
Quantizations
1
Registered
2026-09-10 10:55
Last updated on HF
2026-09-10 13:00
Source huggingface.co/mradermacher/Muse-Glimmer-30B-Uncensored-Heretic-i1-GGUF ↗

Files by quantization

Auxiliary files 3 files 12.8 MB
Muse-Glimmer-30B-Uncensored-Heretic.imatrix.gguf 12.8 MB 87cab31c download
.gitattributes 1.57 KB 03c60b6d download
README.md 493 B 351bda1d download

README current version from Hugging Face

README history 4 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-09-10auto-patch README.mdff4f1586.9 KB
    Loading...
  2. 2026-09-10auto-patch README.mdea0925e5.3 KB
    Loading...
  3. 2026-09-10auto-patch README.md95650862.8 KB
    Loading...
  4. 2026-09-10uploaded from nico1d6b93a5493 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.

Get the app Browse the catalog
Open in Abliteration