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

rAIfle/llama-3-70B-Instruct-abliterated-exl2

rAIfle Llama 70B
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/rAIfle%2Fllama-3-70B-Instruct-abliterated-exl2"
Response includes
  • classification m1
  • files 3
  • hub_downloads_all_time 5
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=llama&method=m1
Sibling llama models · same method
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
5
0
Likes
1
Model age
2.4y ago
created 2024-05-07
Downloads over time
Now5→from2↑150%
0816242 on Jul 24, 20245 on Oct 1122 on Feb 26, 2025Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Metadata

Tags
region:us
Total size
0 B
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-05-15 13:44
Source huggingface.co/rAIfle/llama-3-70B-Instruct-abliterated-exl2 ↗

Files by quantization

Auxiliary files 3 files 4.26 MB
measurement.json 4.26 MB 5dded3d1 download
.gitattributes 1.48 KB a6344aac download
README.md 509 B c133b6b2 download

README current version from Hugging Face

EXL2 quants of failspy/llama-3-70B-Instruct-abliterated

Branches:

  • main -- measurement.json
  • 2.25b6h -- 2.25bpw, 6bit lm_head
  • 3.5b6h -- 3.5bpw, 6bit lm_head
  • 3.75b6h -- 3.75bpw, 6bit lm_head
  • 4b6h -- 4bpw, 6bit lm_head
  • 4.5b6h -- 4.5bpw, 6bit lm_head
  • 4.65b6h -- 4.65bpw, 6bit lm_head
  • 6b6h -- 6bpw, 6bit lm_head
  • 8b8h -- 8bpw, 8bit lm_head

No rpcal for this one, just a normal batch of standard-settings exl2.

README history 11 versions

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

  1. 2024-05-15Update README.md2318c87509 B
    Loading...
  2. 2024-05-08Update README.mda573822478 B
    Loading...
  3. 2024-05-08Create README.mdd5fbd3a455 B
    Loading...
  4. 2024-05-07Upload folder using huggingface_hub6feca052.1 KB
    Loading...
  5. 2024-05-07Upload folder using huggingface_hub3ebf3002.1 KB
    Loading...
  6. 2024-05-07Upload folder using huggingface_hub6480f562.1 KB
    Loading...
  7. 2024-05-07Upload folder using huggingface_hubafa773a2.1 KB
    Loading...
  8. 2024-05-07Upload folder using huggingface_hubfaa23672.1 KB
    Loading...
  9. 2024-05-07Upload folder using huggingface_hubf4652f72.1 KB
    Loading...
  10. 2024-05-07Upload folder using huggingface_hubae59d832.1 KB
    Loading...
  11. 2024-05-07Upload folder using huggingface_hub95fd5d82.1 KB
    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