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

DarkArtsForge/huihui-ai_Huihui-GLM-4.5-Air-abliterated-Q3_K_M-GGUF

DarkArtsForge Glm 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/DarkArtsForge%2Fhuihui-ai_Huihui-GLM-4.5-Air-abliterated-Q3_K_M-GGUF"
Response includes
  • classification m8
  • files 8
  • hub_downloads_all_time 1,170
  • author_summary 1 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)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
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 · lifetime
1K
40 last 30d - cooling
Likes
1
Model age
9mo ago
created 2026-01-04
Downloads over time
Now1.2K→from4↑29,525%
04348691.3K4 on Jan 71.2K on Oct 111.2K on Oct 10JanMarMayJulSep
Jan 7 → Oct 11 · 79 snapshots · spans 277 days

Metadata

Tags
gguf endpoints_compatible region:us conversational
Total size
53.1 GB
Files
8
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-22 10:27

Files by quantization

Auxiliary files 8 files 53.1 GB
Q3_K_M-GGUF-00002-of-00006.gguf 9.29 GB ecdb375c download
Q3_K_M-GGUF-00003-of-00006.gguf 9.29 GB 6f8678e2 download
Q3_K_M-GGUF-00001-of-00006.gguf 9.29 GB 6ac70113 download
Q3_K_M-GGUF-00004-of-00006.gguf 9.04 GB 3c2a5217 download
Q3_K_M-GGUF-00005-of-00006.gguf 8.99 GB 5dcefa75 download
Q3_K_M-GGUF-00006-of-00006.gguf 7.21 GB 44732bfc download
.gitattributes 1.88 KB c8739f38 download
README.md 806 B 10588002 download

README current version from Hugging Face

saved from huihui's repo before the Q3_K_M was deleted

https://huggingface.co/huihui-ai/Huihui-GLM-4.5-Air-abliterated-GGUF/tree/main/Q3_K_M-GGUF

useful for 64gb ram

this is the setup I use with 8gb vram

koboldcpp.exe --host 0.0.0.0 --port 5001 --model Q3_K_M-GGUF-00001-of-00006.gguf --flashattention --contextsize 57344 --gpulayers 22 --moecpu

or

koboldcpp.exe --host 0.0.0.0 --port 5001 --model Q3_K_M-GGUF-00001-of-00006.gguf --flashattention --contextsize 16384 --gpulayers 48 --moecpu

this model is really good but i recommend mlabonne's abliterated gemma 3 27B for cases when GLM struggles with prompt adherence

Update

the original model has been deleted. here are the safetensors upconverted from Q4_K_M

README history 4 versions

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

  1. 2026-05-22Update README.md482b61c806 B
    Loading...
  2. 2026-01-23Update README.mdba43cbb631 B
    Loading...
  3. 2026-01-09Update README.md48fdc28481 B
    Loading...
  4. 2026-01-09Create README.md7fb3ffe351 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