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

swdjojo/Huihui-Agents-A1-abliterated-oQ8e

swdjojo 35B MoE multimodal second-order
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/swdjojo%2FHuihui-Agents-A1-abliterated-oQ8e"
Response includes
  • classification m1
  • files 18
  • hub_downloads_all_time 108
  • author_summary 12 models
  • readme_text full
Try next
GET/models?author=swdjojo
All 12 models by swdjojo
 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 · lifetime
108
30 last 30d - stable
Likes
0
Model age
2mo ago
created 2026-08-11
Downloads over time
Now112→from0↑0%
041821230 on Aug 12112 on Oct 11112 on Oct 9AugSepOct
Aug 12 → Oct 11 · 49 snapshots · spans 60 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

huihui-ai/Huihui-Agents-A1-abliterated↓ 175 this lineage
swdjojo/Huihui-Agents-A1-abliterated-oQ8e↓ 30

Metadata

Tags
mlx safetensors qwen3_5_moe oq quantized image-text-to-text conversational base_model:huihui-ai/Huihui-Agents-A1-abliterated base_model:quantized:huihui-ai/Huihui-Agents-A1-abliterated 8-bit region:us

Related

Other by swdjojo
Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-oQ4e-mtp 404 Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-oQ8e-mtp 295 Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-oQ6e-mtp 253 Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-oQ5e-mtp 187 Huihui-Agents-A1-abliterated-oQ4e 63
Same base model
mradermacher/Huihui-Agents-A1-abliterated-i1-GGUF 7K mradermacher/Huihui-Agents-A1-abliterated-GGUF 4K swdjojo/Huihui-Agents-A1-abliterated-oQ4e 63 swdjojo/Huihui-Agents-A1-abliterated-oQ6e 15 swdjojo/Huihui-Agents-A1-abliterated-oQ5e 13
Total size
35.1 GB
Files
18
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-11 14:52
Source huggingface.co/swdjojo/Huihui-Agents-A1-abliterated-oQ8e ↗ Base model huihui-ai/Huihui-Agents-A1-abliterated →

Files by quantization

Auxiliary files 18 files 35.1 GB
model-00001-of-00008.safetensors 4.83 GB 98b2957b download
model-00004-of-00008.safetensors 4.78 GB 3adbde11 download
model-00006-of-00008.safetensors 4.78 GB 1383467d download
model-00007-of-00008.safetensors 4.78 GB b08ccd4e download
model-00005-of-00008.safetensors 4.78 GB ee32cbb1 download
model-00003-of-00008.safetensors 4.78 GB 5841dd5a download
model-00002-of-00008.safetensors 4.78 GB 64c630cc download
model-00008-of-00008.safetensors 1.59 GB b9df6d26 download
tokenizer.json 19.1 MB 87a7830d download
model.safetensors.index.json 196 KB 12f4ea5e download
config.json 71.8 KB f9c5422d download
oq_imatrix_report.json 31.1 KB 0f2371fb download
tokenizer_config.json 16.3 KB eda48d3e download
chat_template.jinja 7.57 KB a585dec8 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.16 KB 33818c7f download
README.md 609 B fab980b4 download
preprocessor_config.json 390 B 2ea84a43 download

README current version from Hugging Face

library_name: mlx
tags:

  • mlx
  • oq
  • quantized
    base_model:
  • huihui-ai/Huihui-Agents-A1-abliterated
    pipeline_tag: image-text-to-text

[!IMPORTANT]
This quantization was uploaded on 2026-08-11 and replaces a previous version.
If you downloaded this model before this date, please re-download for the updated weights.

Huihui-Agents-A1-abliterated-oQ8e

This model was quantized using oQ (oMLX v0.5.8.dev3) mixed-precision quantization.

Quantization details

  • Model type: qwen3_5_moe
  • Bits: 8
  • Group size: 64
  • Format: MLX safetensors

README history 2 versions

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

  1. 2026-08-11Update README.md23bdcca609 B
    Loading...
  2. 2026-08-11Upload Huihui-Agents-A1-abliterated-oQ8e via oMLX84393e3524 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