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

Melvin56/Dria-Agent-a-3B-abliterated-GGUF

Melvin56 Qwen 3B GGUF second-order 33K 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/Melvin56%2FDria-Agent-a-3B-abliterated-GGUF"
Response includes
  • classification m8
  • files 12
  • hub_downloads_all_time 1,457
  • author_summary 28 models
  • readme_text full
Try next
GET/models?author=Melvin56
All 28 models by Melvin56
 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
1K
169 last 30d - stable
Likes
0
Model age
20mo ago
created 2025-02-05
Downloads over time
Now1.5K→from187↑707%
1216281.1K1.6K187 on Feb 5, 20251.5K on Oct 11Feb '25May '25Aug '25Nov '25FebMayAug
Feb 5, 2025 → Oct 11 · 127 snapshots · spans 613 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/Dria-Agent-a-3B-abliterated this lineage
Melvin56/Dria-Agent-a-3B-abliterated-GGUF↓ 169

Metadata

License
other
Languages
en
Quantizations
F16 Q2_K Q3_K Q4 Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf code chat qwen qwen-coder agent abliterated uncensored text-generation en license:other

Related

Other by Melvin56
DeepSeek-R1-Distill-Qwen-7B-abliterated-v2-GGUF 4K Phi-4-mini-instruct-abliterated-GGUF 1K GLM-4-9B-0414-abliterated-GGUF 988 Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_M-GGUF 487 GLM-Z1-9B-0414-abliterated-GGUF 458
Same base model
mradermacher/Dria-Agent-a-3B-abliterated-i1-GGUF 566 mradermacher/Dria-Agent-a-3B-abliterated-GGUF 249 MaziyarPanahi/Dria-Agent-a-3B-abliterated-GGUF 117
Total size
20.5 GB
Files
12
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2025-02-05 13:20
Source huggingface.co/Melvin56/Dria-Agent-a-3B-abliterated-GGUF ↗ Base model huihui-ai/Dria-Agent-a-3B-abliterated ↗

Files by quantization

F16 1 file 5.75 GB
dria-agent-a-3b-abliterated-f16.gguf 5.75 GB 5d2c5289 download
Q8_0 1 file 3.06 GB
dria-agent-a-3b-abliterated-Q8_0.gguf 3.06 GB 6c20a88a download
Q6_K 1 file 2.36 GB
dria-agent-a-3b-abliterated-Q6_K.gguf 2.36 GB 994e2dfb download
Q5_K 1 file 2.07 GB
dria-agent-a-3b-abliterated-Q5_K_M.gguf 2.07 GB e5022740 download
Q4_K 1 file 1.80 GB
dria-agent-a-3b-abliterated-Q4_K_M.gguf 1.80 GB d36342e1 download
Q4 1 file 1.70 GB
dria-agent-a-3b-abliterated-Q4_0.gguf 1.70 GB 10a4c09b download
Q3_K 1 file 1.48 GB
dria-agent-a-3b-abliterated-Q3_K_M.gguf 1.48 GB b528bc78 download
Q2_K 2 files 2.30 GB
dria-agent-a-3b-abliterated-Q2_K.gguf 1.19 GB 1212af99 download
dria-agent-a-3b-abliterated-Q2_K_S.gguf 1.12 GB 8c1e0aad download
Auxiliary files 3 files 3.21 MB
imatrix.dat 3.21 MB 7dc58bbb download
.gitattributes 2.19 KB f2a5b1d9 download
README.md 940 B 1ecac7f5 download

README current version from Hugging Face

license: other
license_name: qwen-research
license_link: https://huggingface.co/huihui-ai/Dria-Agent-a-3B-abliterated/blob/main/LICENSE
language:

  • en
    base_model:
  • huihui-ai/Dria-Agent-a-3B-abliterated
    pipeline_tag: text-generation
    library_name: transformers
    tags:
  • code
  • chat
  • qwen
  • qwen-coder
  • agent
  • abliterated
  • uncensored

Melvin56/Dria-Agent-a-3B-abliterated-GGUF

Original Model : huihui-ai/Dria-Agent-a-3B-abliterated

All quants are made using the imatrix option.

Model Size (GB)
Q2_K_S 1.19
Q2_K 1.27
Q3_K_M 1.60
Q3_K_M 1.60
Q4_0 1.83
Q4_K_M 1.92
Q5_K_M 2.22
Q6_K 2.53
Q8_0 3.28
F16 6.17

README history 2 versions

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

  1. 2025-02-05Update README.mde768f06940 B
    Loading...
  2. 2025-02-05Upload model via Google Colab26efb4a766 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