← back to catalog · registered 2026-11-11 16:03

mradermacher/Muse-Glimmer-30B-abliterated-v4-GGUF

mradermacher 30B GGUF
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-abliterated-v4-GGUF"
Response includes
  • classification m8
  • files 8
  • author_summary 3602 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 signals
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.
  • author=mradermacher (M8 quantization producer)
  • is_gguf=1
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
1K
Likes
0
Model age
1w ago
created 2026-11-11
Downloads over time
Now 1.3K → from 0 ↑ 0%
04689351.4K 0 on Nov 11 1.3K on Nov 22 Nov
Nov 11 → Nov 22 · 12 snapshots · spans 11 days

Variants by this author 2 formats · 8K downloads combined

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

Metadata

Quantizations
Q2_K Q4_K Q6_K Q8_0
Tags
transformers gguf en base_model:jsantillana/Muse-Glimmer-30B-abliterated-v4 base_model:quantized:jsantillana/Muse-Glimmer-30B-abliterated-v4 endpoints_compatible region:us conversational

Related

Total size
73.9 GB
Files
8
Quantizations
6
Registered
2026-11-11 16:03
Last updated on HF
2026-11-11 16:49

Files by quantization

Q8_0 2 files 29.5 GB
Muse-Glimmer-30B-abliterated-v4.Q8_0.gguf 27.6 GB 25591bee download
Muse-Glimmer-30B-abliterated-v4.mmproj-Q8_0.gguf 1.91 GB 625d1052 download
Q6_K 1 file 21.3 GB
Muse-Glimmer-30B-abliterated-v4.Q6_K.gguf 21.3 GB 74f609eb download
Q4_K 1 file 15.0 GB
Muse-Glimmer-30B-abliterated-v4.Q4_K_S.gguf 15.0 GB 943be18b download
Q2_K 1 file 9.95 GB
Muse-Glimmer-30B-abliterated-v4.Q2_K.gguf 9.95 GB 6aec9d69 download
F16 1 file 3.58 GB
Muse-Glimmer-30B-abliterated-v4.mmproj-f16.gguf 3.58 GB ee1ca28b download
Auxiliary files 2 files 2.33 KB
.gitattributes 1.96 KB 3c96f9aa download
README.md 386 B 42c8cdbe download

README current version from Hugging Face

README history 3 versions

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

  1. 2026-11-11 auto-patch README.md 761c521 4.3 KB
    Loading...
  2. 2026-11-11 auto-patch README.md c4c58b7 4.2 KB
    Loading...
  3. 2026-11-11 uploaded from nico1 b6d8eb2 386 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.

Open in Abliteration