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

samch183/abliterated-model-fp16

samch183 Llama 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/samch183%2Fabliterated-model-fp16"
Response includes
  • classification m1
  • files 12
  • hub_downloads_all_time 183
  • 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
183
8 last 30d - cooling
Likes
0
Model age
6mo ago
created 2026-03-17
Downloads over time
Now185→from149↑24%
147161175189149 on Mar 18185 on Oct 11185 on Oct 4MarAprMayJunJulAugSepOct
Mar 18 → Oct 11 · 69 snapshots · spans 207 days

Metadata

Tags
safetensors llama region:us
Total size
15.0 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-17 04:49

Files by quantization

Auxiliary files 12 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB 6611b222 download
model-00001-of-00004.safetensors 4.63 GB 19aa7545 download
model-00003-of-00004.safetensors 4.58 GB ccc32c92 download
model-00004-of-00004.safetensors 1.09 GB 3732d6e2 download
tokenizer.json 8.66 MB 5cc5f00a download
tokenizer_config.json 49.7 KB 421cda36 download
model.safetensors.index.json 23.4 KB 6a4b5e52 download
.gitattributes 1.48 KB a6344aac download
config.json 853 B ec1f9e0c download
special_tokens_map.json 296 B 02ee80b6 download
generation_config.json 194 B 77789f31 download
test.json 14.0 B a6d6f537 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