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

BobSteven/ministral-8b-abliterated

BobSteven Mistral 8.0B
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/BobSteven%2Fministral-8b-abliterated"
Response includes
  • classification m1
  • files 11
  • hub_downloads_all_time 27
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
27
8 last 30d - stable
Likes
1
Descendants
2
in 2 direct forks
Model age
9mo ago
created 2025-12-25
Downloads over time
Now28→from10↑180%
111213110 on Dec 24, 202528 on Oct 1128 on Oct 6Dec '25FebAprJunAugOct
Dec 24, 2025 → Oct 11 · 81 snapshots · spans 291 days

Genealogy 2 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

Tags
safetensors mistral region:us
Total size
14.9 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-12-25 11:49

Files by quantization

Auxiliary files 11 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB 9855486a download
model-00003-of-00004.safetensors 4.64 GB 3c4997da download
model-00001-of-00004.safetensors 4.64 GB 7c295477 download
model-00004-of-00004.safetensors 1.00 GB e75c6183 download
tokenizer.json 16.3 MB d7edbeaf download
tokenizer_config.json 177 KB 31c439d2 download
model.safetensors.index.json 26.3 KB 2247a456 download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.38 KB 586a3f9f download
special_tokens_map.json 414 B 451134b2 download
generation_config.json 116 B 9ef6c5a0 download

README

The author did not publish a README.

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