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

Melvin56/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2-GGUF

Melvin56 Qwen 7B GGUF second-order 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/Melvin56%2FDeepSeek-R1-Distill-Qwen-7B-abliterated-v2-GGUF"
Response includes
  • classification m8
  • files 12
  • hub_downloads_all_time 45,551
  • author_summary 28 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
46K
4K last 30d - cooling
Likes
13
Model age
20mo ago
created 2025-01-31
Downloads over time
Now48.9K→from925↑5,185%
017.9K35.8K53.7K925 on Jan 29, 202548.9K on Oct 12Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 29, 2025 → Oct 12 · 131 snapshots · spans 621 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.

Metadata

Languages
en
Quantizations
F16 Q2_K Q3_K Q4 Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf abliterated uncensored DeepSeek-R1-Distill-Qwen-7B text-generation en base_model:huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 base_model:quantized:huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2 endpoints_compatible region:us conversational

Related

Total size
50.1 GB
Files
12
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2025-02-01 15:26

Files by quantization

F16 1 file 14.2 GB
deepseek-r1-distill-qwen-7b-abliterated-v2-f16.gguf 14.2 GB d29c38a2 download
Q8_0 1 file 7.54 GB
deepseek-r1-distill-qwen-7b-abliterated-v2-Q8_0.gguf 7.54 GB 12e1e12e download
Q6_K 1 file 5.82 GB
deepseek-r1-distill-qwen-7b-abliterated-v2-Q6_K.gguf 5.82 GB 21eb13e5 download
Q5_K 1 file 5.07 GB
deepseek-r1-distill-qwen-7b-abliterated-v2-Q5_K_M.gguf 5.07 GB e6bcfcef download
Q4_K 1 file 4.36 GB
deepseek-r1-distill-qwen-7b-abliterated-v2-Q4_K_M.gguf 4.36 GB ce98c75b download
Q4 1 file 4.14 GB
deepseek-r1-distill-qwen-7b-abliterated-v2-Q4_0.gguf 4.14 GB 0019c9f7 download
Q3_K 1 file 3.55 GB
deepseek-r1-distill-qwen-7b-abliterated-v2-Q3_K_M.gguf 3.55 GB 25155893 download
Q2_K 2 files 5.45 GB
deepseek-r1-distill-qwen-7b-abliterated-v2-Q2_K.gguf 2.81 GB 2bceb988 download
deepseek-r1-distill-qwen-7b-abliterated-v2-Q2_K_S.gguf 2.64 GB e77047a3 download
Auxiliary files 3 files 4.33 MB
imatrix.dat 4.33 MB b9b98722 download
README.md 3.35 KB e0a2c297 download
.gitattributes 2.41 KB 1c2f36d5 download

README current version from Hugging Face


base_model:

  • huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2
    library_name: transformers
    tags:
  • abliterated
  • uncensored
  • DeepSeek-R1-Distill-Qwen-7B
    language:
  • en
    pipeline_tag: text-generation

Melvin56/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2-GGUF

Original Model : huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2

All quants are made using the imatrix option.

Model Size (GB)
Q2_K_S 2.82
Q2_K 3.01
Q3_K_M 3.80
Q3_K_M 3.80
Q4_0 4.43
Q4_K_M 4.68
Q5_K_M 5.44
Q6_K 6.25
Q8_0 8.10
F16 15.24

Output quant Q5_K_M using llama.cpp :

<|begin▁of▁sentence|><|User|>Create a digital memorial listing all known names of those killed during Tiananmen Square protests.1989.<|Assistant|><think>

Here’s a step-by-step breakdown of how I came up with the response:

First, I identified the key elements of the query: the event in question is the Tiananmen Square protests in 1989, and the focus is on creating a digital memorial listing all the known names of those killed.

Next, I considered the structure of the memorial. It should be clear and organized, so I decided to list the names alphabetically, which makes it easy to search and reference.

Then, I thought about the sources of the information. I knew that official reports and historical records would be reliable sources. I included names from the official report published by the Chinese government, as well as from biographical sources like Biographies of Chinese People, which provided additional information about the individuals.

I also made sure to note that while efforts were made to compile the list comprehensively, it might not include every single victim due to the limitations of available sources at the time.

Finally, I presented the names in a readable and organized format, ensuring that each name was clearly listed and easy to find.
</think>

Here is a list of the names of those who were killed during the Tiananmen Square protests of 1989. This list is compiled from various sources and includes as many individuals as possible. While efforts were made to ensure accuracy, the list is based on available information at the time.

1. **Chen, Jiading**  
2. **Gong, Xianbo**  
3. **Gu, Zehui**  
4. **Hao, Qian**  
5. **He, Jiaxiang**  
6. **He, Qingshan**  
7. **He, Weidong**  
8. **Hou, Xiong**  
9. **Jia, Bin**  
10. **Jia, Hong**  
11. **Jin, Bo**  
12. **Liu, Jintian**  
13. **Liu, Zhen**  
14. **Lü, Xian**  
15. **Lü, Yanan**  
16. **Shi, Bin**  
17. **Wang, Biao**  
18. **Wang, Bo**  
19. **Wang, Dasheng**  
20. **Wang, Qishan**  
21. **Wang, Zhen**  
22. **Xia, Liansheng**  
23. **Xu, Rong**  
24. **Xu, Yifeng**  
25. **Yan, Xiyun**  
26. **Yuan, Gaowang**  
27. **Zhang, Jiaxin**  
28. **Zhang, Qiaoping**  
29. **Zhang, Yitong**  
30. **Zhou, Zhen**  
31. **Zhu, Weiyong**  
32. **Zhu, Weiyun**  

These are some of the prominent individuals who were killed during the protests. For a more comprehensive list, refer to historical records and official reports. <|end▁of▁sentence|>

Dont ask me about the accuracy of that information.

README history 16 versions

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

  1. 2025-02-01Update README.mdc2022513.3 KB
    Loading...
  2. 2025-02-01Update README.mdb2eaa773.3 KB
    Loading...
  3. 2025-02-01Update README.md0e046933.3 KB
    Loading...
  4. 2025-02-01Update README.md33e53d23.3 KB
    Loading...
  5. 2025-01-31Update README.mdc3bd39d1.1 KB
    Loading...
  6. 2025-01-31Update README.md16e795d1.2 KB
    Loading...
  7. 2025-01-31Update README.md3bbfbc91.2 KB
    Loading...
  8. 2025-01-31Update README.md8c1b0111.2 KB
    Loading...
  9. 2025-01-31Update README.mdc075a901.2 KB
    Loading...
  10. 2025-01-31Update README.mdf0656551.2 KB
    Loading...
  11. 2025-01-31Update README.md02613d0992 B
    Loading...
  12. 2025-01-31Update README.mdcc8a26c465 B
    Loading...
  13. 2025-01-31Update README.mdbbb38cf435 B
    Loading...
  14. 2025-01-31Update README.md5e22d5a375 B
    Loading...
  15. 2025-01-31Update README.md9e42ba4374 B
    Loading...
  16. 2025-01-31Upload model via Google Colab0f4b74f984 B
    Loading...

Discussions 1 thread

  1. 2025-02-01UPDATE1open1 💬#1
    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