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

thisnick/Llama-3.3-70B-Instruct-abliterated-GGUF

thisnick Llama 70B GGUF 131K ctx
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%2FLlama-3.3-70B-Instruct-abliterated-GGUF"
Response includes
  • classification m8
  • files 6
  • hub_downloads_all_time 230
  • author_summary 15 models
  • readme_text full
Try next
GET/models?author=thisnick
All 15 models by thisnick
 GET/models?family=llama&method=m8
Sibling llama models · same method
 GET/methods/m8
What "m8" means · taxonomy
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
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 · lifetime
230
Likes
0
Model age
20mo ago
created 2025-01-30
Downloads over time
Now494→from164↑201%
0181362543164 on Jan 29, 2025494 on Oct 11Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 29, 2025 → Oct 11 · 128 snapshots · spans 620 days

Variants by this author 2 formats · 461 downloads combined

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

Metadata

License
apache-2.0
Languages
en
Quantizations
Q2_K Q3_K Q4_K Q5_K
Tags
gguf autoquant en license:apache-2.0 endpoints_compatible region:us conversational

Related

Other by thisnick
Llama-3.1-8B-Instruct-abliterated-GGUF 195 DeepSeek-R1-Distill-Llama-70B-abliterated-GGUF 125 DeepSeek-R1-Distill-Llama-70B-abliterated-FP8-Dynamic 103 Llama-3.1-70B-Instruct-abliterated-GGUF 81 DeepSeek-R1-Distill-Llama-8B-abliterated-GGUF 70
Total size
143 GB
Files
6
Quantizations
5
Registered
2026-08-22 13:56
Last updated on HF
2025-01-30 07:36
Source huggingface.co/thisnick/Llama-3.3-70B-Instruct-abliterated-GGUF ↗

Files by quantization

Q5_K 1 file 46.5 GB
llama-3.3-70b-instruct-abliterated.Q5_K_M.gguf 46.5 GB 2ef402ba download
Q4_K 1 file 39.6 GB
llama-3.3-70b-instruct-abliterated.Q4_K_M.gguf 39.6 GB ffaa8eeb download
Q3_K 1 file 31.9 GB
llama-3.3-70b-instruct-abliterated.Q3_K_M.gguf 31.9 GB ca9254c0 download
Q2_K 1 file 24.6 GB
llama-3.3-70b-instruct-abliterated.Q2_K.gguf 24.6 GB f64241c4 download
Auxiliary files 2 files 2.08 KB
.gitattributes 1.81 KB f978ddc6 download
README.md 281 B 406ad8ce download

README current version from Hugging Face

README history 1 version

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

  1. 2025-01-30Add files using upload-large-folder tool362e699281 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 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.

Get the app Browse the catalog
Open in Abliteration