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

dzsoszmissz/Huihui-Qwen3.6-35B-A3B-abliterated-betQ5

dzsoszmissz Qwen 35B GGUF MoE multimodal 262K 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/dzsoszmissz%2FHuihui-Qwen3.6-35B-A3B-abliterated-betQ5"
Response includes
  • classification m8
  • files 5
  • hub_downloads_all_time 650
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=dzsoszmissz
All 3 models by dzsoszmissz
 GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
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
M1 Direct removal →
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
How we label → About M8 →
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
650
91 last 30d - stable
Likes
0
Model age
4mo ago
created 2026-06-11
Downloads over time
Now673→from39↑1,626%
725049373639 on Jun 10673 on Oct 11JunJulAugSepOct
Jun 10 → Oct 11 · 57 snapshots · spans 123 days

Metadata

Quantizations
Q5_K
Tags
gguf qwen3_5_moe llama.cpp unsloth vision-language-model endpoints_compatible region:us conversational

Related

Other by dzsoszmissz
Huihui-Qwen3.6-35B-A3B-abliterated-bet-GGUF 97 Huihui-Qwen3.6-35B-A3B-abliterated-bet 0
Total size
23.6 GB
Files
5
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2026-06-11 11:20
Source huggingface.co/dzsoszmissz/Huihui-Qwen3.6-35B-A3B-abliterated-betQ5 ↗

Files by quantization

Q5_K 1 file 23.6 GB
Huihui-Qwen3.6-35B-A3B-abliterated.Q5_K_M.gguf 23.6 GB 24cb366a download
mmproj 1 file 861 MB
Huihui-Qwen3.6-35B-A3B-abliterated.BF16-mmproj.gguf 861 MB 2fcb9308 download
Auxiliary files 3 files 6.22 KB
config.json 3.76 KB 238c4d75 download
.gitattributes 1.65 KB 8e3e0371 download
README.md 833 B 1ae59e41 download

README current version from Hugging Face

tags:

  • gguf
  • llama.cpp
  • unsloth
  • vision-language-model

Huihui-Qwen3.6-35B-A3B-abliterated-betQ5 : GGUF

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

  • For text only LLMs: llama-cli -hf dzsoszmissz/Huihui-Qwen3.6-35B-A3B-abliterated-betQ5 --jinja
  • For multimodal models: llama-mtmd-cli -hf dzsoszmissz/Huihui-Qwen3.6-35B-A3B-abliterated-betQ5 --jinja

Available Model files:

  • Huihui-Qwen3.6-35B-A3B-abliterated.Q5_K_M.gguf
  • Huihui-Qwen3.6-35B-A3B-abliterated.BF16-mmproj.gguf
    This was trained 2x faster with Unsloth

README history 1 version

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

  1. 2026-06-11Add README3d38820833 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