← back to catalog · registered 2026-11-21 09:04

lecheyne24/mistral-7b-abliterated

lecheyne24 Mistral 7B GGUF
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/lecheyne24%2Fmistral-7b-abliterated"
Response includes
  • classification m8
  • files 4
  • author_summary 6 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 · 30-day
0
Likes
0
Model age
2d ago
created 2026-11-19

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

Quantizations
Q4_K
Tags
llama.cpp gguf abliterated uncensored mistral text-generation base_model:mistralai/Mistral-7B-Instruct-v0.3 base_model:quantized:mistralai/Mistral-7B-Instruct-v0.3 endpoints_compatible region:us conversational

Related

Control vectors

Total size
8.15 GB
Files
4
Quantizations
2
Registered
2026-11-21 09:04
Last updated on HF
2026-11-21 07:48

Files by quantization

Q4_K 2 files 8.15 GB
Mistral-7B-Instruct-v0.3-abliterated.Q4_K_M.gguf 4.07 GB a53f0632 download
mistral-7b-unbound.Q4_K_M.gguf 4.07 GB 8f0108f6 download
Auxiliary files 2 files 2.36 KB
.gitattributes 1.63 KB a8d0dfb8 download
README.md 743 B 6ed0b061 download

README current version from Hugging Face


base_model: mistralai/Mistral-7B-Instruct-v0.3
library_name: llama.cpp
tags:

  • abliterated
  • uncensored
  • gguf
  • mistral
  • text-generation
    quantized_by: lecheyne24

mistral-7b-abliterated (Q4_K_M, GGUF)

Uncensored build of mistralai/Mistral-7B-Instruct-v0.3.

  • Method: refusal-direction rank-1 norm-preserving biprojection (o_proj + down_proj), alpha 1.25, all layers.
  • Quant: Q4_K_M
  • Files: Mistral-7B-Instruct-v0.3-abliterated.Q4_K_M.gguf, mistral-7b-unbound.Q4_K_M.gguf
  • Plain-answer gauntlet: 7/8. Only miss: financial-call answered "positive growth" instead of committing "higher".

Run

llama-server -m Mistral-7B-Instruct-v0.3-abliterated.Q4_K_M.gguf --port 8083 -c 4096 --alias mistral-7b
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