Get the app
← back to catalog · registered 2026-09-18 10:56

timteh673/Muse-Glimmer-30B-Abliterated-oQ8e

timteh673 30B 
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/timteh673%2FMuse-Glimmer-30B-Abliterated-oQ8e"
Response includes
  • classification m1
  • files 17
  • author_summary 8 models
  • readme_text full
Try next
GET/models?author=timteh673
All 8 models by timteh673
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 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.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-09-18

Metadata

Tags
mlx safetensors muse_glimmer oq quantized 8-bit region:us

Related

Other by timteh673
Qwen3.5-397B-A17B-Uncensored-GGUF 2K Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF 2K Nemotron-Super-49B-v1.5-Uncensored-GGUF 1K Mistral-Small-4-119B-Uncensored-GGUF 1K Nemotron-3-Super-120B-A12B-Uncensored-GGUF 1K
Total size
31.1 GB
Files
17
Quantizations
1
Registered
2026-09-18 10:56
Last updated on HF
2026-09-18 10:11
Source huggingface.co/timteh673/Muse-Glimmer-30B-Abliterated-oQ8e ↗

Files by quantization

Auxiliary files 17 files 31.2 GB
model-00002-of-00007.safetensors 4.71 GB 712ee952 download
model-00006-of-00007.safetensors 4.69 GB 2620dba8 download
model-00001-of-00007.safetensors 4.68 GB 6debd8e1 download
model-00005-of-00007.safetensors 4.66 GB 30527b2c download
model-00004-of-00007.safetensors 4.66 GB 79bf56ab download
model-00003-of-00007.safetensors 4.66 GB 090a4b66 download
model-00007-of-00007.safetensors 3.09 GB 81d1b917 download
tokenizer.json 26.8 MB c9dbee66 download
model.safetensors.index.json 204 KB c61c2e38 download
tokenizer_config.json 87.5 KB 6413515e download
oq_imatrix_report.json 24.9 KB 942fa5dc download
chat_template.jinja 9.31 KB 6fbdf45f download
config.json 5.20 KB 23bceeea download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.06 KB ec9a07be download
README.md 525 B 5cda7829 download
generation_config.json 148 B 3495c31e download

README current version from Hugging Face

library_name: mlx
tags:

  • mlx
  • oq
  • quantized

[!IMPORTANT]
This quantization was uploaded on 2026-09-18 and replaces a previous version.
If you downloaded this model before this date, please re-download for the updated weights.

Muse-Glimmer-30B-Abliterated-oQ8e

This model was quantized using oQ (oMLX v0.7.0.dev2) mixed-precision quantization.

Quantization details

  • Model type: muse_glimmer
  • Bits: 8
  • Group size: 64
  • Format: MLX safetensors
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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.

See supported apps Browse the catalog