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

JamePeng2023/Llama-3.2-3B-Instruct-abliterated-SpinQuant-w4a8

JamePeng2023 Llama 3B second-order
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/JamePeng2023%2FLlama-3.2-3B-Instruct-abliterated-SpinQuant-w4a8"
Response includes
  • classification m1
  • files 2
  • hub_downloads_all_time 33
  • 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
33
4 last 30d - stable
Likes
0
Model age
20mo ago
created 2025-02-16
Downloads over time
Now34→from0↑0%
01225370 on Feb 12, 202534 on Oct 1134 on Oct 6Feb '25May '25Aug '25Nov '25FebMayAug
Feb 12, 2025 → Oct 11 · 126 snapshots · spans 606 days

Genealogy 0 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.

huihui-ai/Llama-3.2-3B-Instruct-abliterated↓ 1,714 this lineage
JamePeng2023/Llama-3.2-3B-Instruct-abliterated-SpinQuant-w4a8↓ 4

Metadata

License
llama3.2
Tags
executorch base_model:huihui-ai/Llama-3.2-3B-Instruct-abliterated base_model:quantized:huihui-ai/Llama-3.2-3B-Instruct-abliterated license:llama3.2 region:us

Related

Same base model
mradermacher/Llama-3.2-3B-Instruct-abliterated-GGUF 3K mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF 2K Hasaranga85/Llama-3.2-3B-Instruct-abliterated-Q4_K_M-GGUF 2K MaziyarPanahi/Llama-3.2-3B-Instruct-abliterated-GGUF 2K Rusgus/Llama-3.2-3B-Instruct-abliterated-GGUF 290
Total size
0 B
Files
2
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-02-16 12:42
Source huggingface.co/JamePeng2023/Llama-3.2-3B-Instruct-abliterated-SpinQuant-w4a8 ↗ Base model huihui-ai/Llama-3.2-3B-Instruct-abliterated →

Files by quantization

Auxiliary files 2 files 2.16 KB
.gitattributes 1.55 KB d847216f download
README.md 630 B 6576ac13 download

README current version from Hugging Face

license: llama3.2
base_model:

  • huihui-ai/Llama-3.2-3B-Instruct-abliterated

Using the SpinQuant quantization method from https://github.com/facebookresearch/SpinQuant, I quantized the Llama-3.2-3B-Instruct-abliterated model from https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated.

This quantization is for on-device deployment to Android apps with Executorch.

To make it easier for everyone to quickly test and deploy the Executorch on-device demo, I've also converted the quantized PTH file to PTE format and uploaded it.

2025-02-16 19:40:24,099 - spinquant - INFO - wiki2 ppl is: 11.502239227294922

README history 3 versions

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

  1. 2025-02-16Update README.mdeeeeeea630 B
    Loading...
  2. 2025-02-16Update README.md72d7fe9405 B
    Loading...
  3. 2025-02-16initial commit7502e2926 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