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

thisnick/DeepSeek-R1-Distill-Llama-8B-abliterated

thisnick 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/thisnick%2FDeepSeek-R1-Distill-Llama-8B-abliterated"
Response includes
  • classification m1
  • files 11
  • hub_downloads_all_time 88
  • author_summary 15 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
88
19 last 30d - stable
Likes
0
Model age
19mo ago
created 2025-02-23
Downloads over time
Now97→from4↑2,325%
035711064 on Feb 19, 202597 on Oct 1197 on Oct 10Feb '25May '25Aug '25Nov '25FebMayAug
Feb 19, 2025 → Oct 11 · 125 snapshots · spans 599 days

Variants by this author 2 formats · 89 downloads combined

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

Metadata

Tags
safetensors llama region:us

Related

Total size
15.0 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-02-23 08:54

Files by quantization

Auxiliary files 11 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB c54dae73 download
model-00001-of-00004.safetensors 4.63 GB c3aadd34 download
model-00003-of-00004.safetensors 4.58 GB 456e4616 download
model-00004-of-00004.safetensors 1.09 GB 209b54ae download
tokenizer.json 16.4 MB 26c881aa download
tokenizer_config.json 51.7 KB bf6b163f download
model.safetensors.index.json 23.4 KB 0fd8120f download
.gitattributes 1.53 KB 52373fe2 download
config.json 895 B 4e62249c download
special_tokens_map.json 371 B d53f816e download
generation_config.json 181 B 2702b2b5 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