Get the app
← back to catalog · registered 2026-09-11 17:55

NINI26454/Mistral-Small-24B-Instruct-2501-Abliterated-GGUF

NINI26454 Mistral 24B GGUF second-order
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 · 30-day
0
Likes
0
Model age
today
created 2026-09-11
Downloads over time
Now0→from0↑0%
00110 on Sep 110 on Sep 12Sep
Sep 11 → Sep 12 · 2 snapshots · spans 1 day

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.

venkycs/Mistral-Small-24B-Instruct-2501-Abliterated↓ 314 this lineage
NINI26454/Mistral-Small-24B-Instruct-2501-Abliterated-GGUF

Metadata

License
apache-2.0
Quantizations
Q3_K
Tags
gguf ollama mistral abliterated quantized base_model:venkycs/Mistral-Small-24B-Instruct-2501-Abliterated base_model:quantized:venkycs/Mistral-Small-24B-Instruct-2501-Abliterated license:apache-2.0 endpoints_compatible region:us conversational

Related

Other by NINI26454
Qwen2.5-Coder-32B-Instruct-Abliterated-GGUF 234 Qwen2.5-Coder-7B-Instruct-Abliterated-GGUF 220 Qwen2.5-Coder-14B-Instruct-Abliterated-GGUF 201 Llama-3.1-8B-Instruct-Abliterated-GGUF 144 Huihui-CyberStrike-OffSec-35B-abliterated-GGUF 134
Total size
10.7 GB
Files
4
Quantizations
2
Registered
2026-09-11 17:55
Last updated on HF
2026-09-11 17:56
Source huggingface.co/NINI26454/Mistral-Small-24B-Instruct-2501-Abliterated-GGUF ↗ Base model venkycs/Mistral-Small-24B-Instruct-2501-Abliterated →

Files by quantization

Q3_K 1 file 10.7 GB
Mistral-Small-24B-Instruct-2501-Abliterated-Q3_K_M.gguf 10.7 GB e0550ca2 download
Auxiliary files 3 files 2.96 KB
.gitattributes 1.57 KB 808b0222 download
README.md 989 B 5d727bcb download
Modelfile 426 B 7b57eb2d download

README current version from Hugging Face

license: apache-2.0
base_model: venkycs/Mistral-Small-24B-Instruct-2501-Abliterated
tags:

  • gguf
  • ollama
  • mistral
  • abliterated
  • quantized

Mistral-Small-24B-Instruct-2501-Abliterated-GGUF

Quantized GGUF version of venkycs/Mistral-Small-24B-Instruct-2501-Abliterated.

Provided Files

  • Mistral-Small-24B-Instruct-2501-Abliterated-Q3_K_M.gguf (3-bit medium quantization, 10.9 GB, balanced quality and low VRAM footprint)
  • Modelfile (Ready-to-use Ollama Modelfile)

How to use with Ollama

  1. Download the GGUF and Modelfile to the same directory.
  2. Run:
ollama create Mistral-Small-24B-Abliterated -f Modelfile
ollama run Mistral-Small-24B-Abliterated

How to use with llama.cpp

llama-cli -m Mistral-Small-24B-Instruct-2501-Abliterated-Q3_K_M.gguf -p "Hello, how are you?" -c 16384

EOF
ls -la /teamspace/studios/this_studio/models/export_mistral

README history 1 version

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

  1. 2026-09-11Upload folder using huggingface_hub99e7016989 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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.

See supported apps Browse the catalog