Get the app
← back to catalog · registered 2026-09-14 01:56

necropopeost/Huihui-MiniCPM5-1B-abliterated-mlx-oQ8e

necropopeost 1.1B
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 · lifetime
92
Likes
0
Model age
2d ago
created 2026-09-14
Downloads over time
Now92→from0↑0%
034671010 on Sep 1492 on Sep 16Sep
Sep 14 → Sep 16 · 3 snapshots · spans 2 days

Metadata

Tags
mlx safetensors llama oq quantized 8-bit region:us
Total size
1.07 GB
Files
9
Quantizations
1
Registered
2026-09-14 01:56
Last updated on HF
2026-09-14 01:52
Source huggingface.co/necropopeost/Huihui-MiniCPM5-1B-abliterated-mlx-oQ8e ↗

Files by quantization

Auxiliary files 9 files 1.08 GB
model.safetensors 1.07 GB be442daa download
tokenizer.json 9.44 MB ec0bf9a3 download
oq_imatrix_report.json 9.24 KB a90b0eb4 download
chat_template.jinja 8.85 KB cb2934c4 download
.gitattributes 1.48 KB a6344aac download
config.json 794 B 38e65780 download
README.md 524 B 0b4ccf9f download
tokenizer_config.json 431 B 3bcc734f download
generation_config.json 213 B 73dc79c2 download

README current version from Hugging Face

library_name: mlx
tags:

  • mlx
  • oq
  • quantized

[!IMPORTANT]
This quantization was uploaded on 2026-09-13 and replaces a previous version.
If you downloaded this model before this date, please re-download for the updated weights.

Huihui-MiniCPM5-1B-abliterated-mlx-oQ8e

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

Quantization details

  • Model type: llama
  • Bits: 8
  • Group size: 64
  • Format: MLX safetensors

README history 1 version

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

  1. 2026-09-14Upload Huihui-MiniCPM5-1B-abliterated-mlx-oQ8e via oMLX936dfad524 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 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