Get the app
← back to catalog · registered 2026-09-10 18:55

0xSojalSec/MiniCPM5-2B-Abliterated-Uncensored-GGUF

0xSojalSec 2B 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/0xSojalSec%2FMiniCPM5-2B-Abliterated-Uncensored-GGUF"
Response includes
  • classification m8
  • files 10
  • hub_downloads_all_time 3,980
  • author_summary 26 models
  • readme_text full
Try next
GET/models?author=0xSojalSec
All 26 models by 0xSojalSec
 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
4K
654 last 30d - stable
HF trending score
1
mild recent interest
Likes
9
Model age
6w ago
created 2026-09-10
Downloads over time
Now4.5K→from0↑0%
01.6K3.3K4.9K0 on Sep 104.5K on Oct 26SepOct
Sep 10 → Oct 26 · 47 snapshots · spans 46 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.

mondk/MiniCPM5-2B-Abliterated-Uncensored-Safetensors↓ 318 this lineage
0xSojalSec/MiniCPM5-2B-Abliterated-Uncensored-GGUF↓ 654

Variants by this author 2 formats · 694 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Languages
en zh
Quantizations
F16 IQ3 IQ4 Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf minicpm minicpm5 llama text-generation tool-calling on-device edge-ai en zh base_model:mondk/MiniCPM5-2B-Abliterated-Uncensored-Safetensors base_model:quantized:mondk/MiniCPM5-2B-Abliterated-Uncensored-Safetensors

Related

Other by 0xSojalSec
Qwen3.8-Flash-Next-Uncensored-GSQ-RCO-12-GB-GPU 41K Qwen-Image-2.1-Uncensored-GGUF 40K Qwen-Image-2.1-Uncensored-HF 16K Abliterated-MiMo-V2.6-Distill-Qwen-9B-GGUF-MLX 3K Qwen3.8-27B-full-Uncensored 3K
Same base model
mondk/MiniCPM5-2B-Abliterated-Uncensored-MLX-4Bit 1K mondk/MiniCPM5-2B-Abliterated-Uncensored-Safetensors-Q8_0-GGUF 0 mondk/MiniCPM5-2B-Abliterated-Uncensored-Safetensors-Q6_K-GGUF 0 mondk/MiniCPM5-2B-Abliterated-Uncensored-Safetensors-Q5_K_M-GGUF 0 mondk/MiniCPM5-2B-Abliterated-Uncensored-Safetensors-Q3_K_L-GGUF 0
Total size
16.0 GB
Files
10
Quantizations
9
Registered
2026-09-10 18:55
Last updated on HF
2026-09-10 18:31
Source huggingface.co/0xSojalSec/MiniCPM5-2B-Abliterated-Uncensored-GGUF ↗ Base model mondk/MiniCPM5-2B-Abliterated-Uncensored-Safetensors →

Files by quantization

F16 1 file 4.69 GB
minicpm5-2b-abliterated-F16.gguf 4.69 GB 97234acf download
Q8_0 1 file 2.50 GB
minicpm5-2b-abliterated-Q8_0.gguf 2.50 GB db1c1d96 download
Q6_K 1 file 1.93 GB
minicpm5-2b-abliterated-Q6_K.gguf 1.93 GB fe953312 download
Q5_K 1 file 1.68 GB
minicpm5-2b-abliterated-Q5_K_M.gguf 1.68 GB 45816469 download
Q4_K 1 file 1.45 GB
minicpm5-2b-abliterated-Q4_K_M.gguf 1.45 GB 6996dbcc download
IQ4 1 file 1.33 GB
minicpm5-2b-abliterated-IQ4_XS.gguf 1.33 GB 6e15fad9 download
Q3_K 1 file 1.28 GB
minicpm5-2b-abliterated-Q3_K_L.gguf 1.28 GB ca89a073 download
IQ3 1 file 1.14 GB
minicpm5-2b-abliterated-IQ3_M.gguf 1.14 GB 4920403f download
Auxiliary files 2 files 3.46 KB
.gitattributes 2.67 KB 8fa14726 download
README.md 807 B a1210a66 download

README current version from Hugging Face

license: apache-2.0
language:

  • en
  • zh
    base_model:
  • mondk/MiniCPM5-2B-Abliterated-Uncensored-Safetensors
    pipeline_tag: text-generation
    tags:
  • minicpm
  • minicpm5
  • llama
  • text-generation
  • tool-calling
  • on-device
  • edge-ai

mondk/MiniCPM5-2B-Abliterated-Uncensored-GGUF

This is an uncensored version of openbmb/MiniCPM5-2B created with abliteration.

Looking for a other build? See:

SAFETENSORS: mondk/MiniCPM5-2B-Abliterated-Uncensored-Safetensors

MLX-4Bit: mondk/MiniCPM5-2B-Abliterated-Uncensored-MLX-4Bit

Sorry, there are no other quantization versions available. To download Q2_K, Q3_K_S, Q3_K_M, Q4_K_S, and Q5_K_S, visit mradermacher/MiniCPM5-2B-Abliterated-Uncensored-Safetensors-GGUF

ty!

README history 1 version

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

  1. 2026-09-10Duplicate from mondk/MiniCPM5-2B-Abliterated-Uncensored-GGUF7712a9d807 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