← back to catalog · registered 2026-11-12 06:03

mradermacher/Qwen2.5-Coder-32B-Instruct-abliterated-v3-i1-GGUF

mradermacher 32B GGUF
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/mradermacher%2FQwen2.5-Coder-32B-Instruct-abliterated-v3-i1-GGUF"
Response includes
  • classification m8
  • files 10
  • author_summary 3602 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 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.
  • author=mradermacher (M8 quantization producer)
  • is_gguf=1
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 · 30-day
3K
Likes
0
Model age
1w ago
created 2026-11-12
Downloads over time
Now 2.9K → from 0 ↑ 0%
01.1K2.1K3.2K 0 on Nov 12 2.9K on Nov 22 Nov
Nov 12 → Nov 22 · 11 snapshots · spans 10 days

Variants by this author 2 formats · 4K downloads combined

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

Metadata

Quantizations
IQ2 IQ3 Q2_K Q3_K Q4_K
Tags
transformers gguf abliteration refusal-direction cybersecurity code interpretability research qwen2.5 en es base_model:jsantillana/Qwen2.5-Coder-32B-Instruct-abliterated-v3

Related

Total size
98.6 GB
Files
10
Quantizations
7
Registered
2026-11-12 06:03
Last updated on HF
2026-11-12 08:21

Files by quantization

Q4_K 2 files 36.0 GB
Qwen2.5-Coder-32B-Instruct-abliterated-v3.i1-Q4_K_M.gguf 18.5 GB f567114f download
Qwen2.5-Coder-32B-Instruct-abliterated-v3.i1-Q4_K_S.gguf 17.5 GB bcdebc77 download
Q3_K 1 file 14.8 GB
Qwen2.5-Coder-32B-Instruct-abliterated-v3.i1-Q3_K_M.gguf 14.8 GB 33cc19d1 download
IQ3 2 files 25.8 GB
Qwen2.5-Coder-32B-Instruct-abliterated-v3.i1-IQ3_M.gguf 13.8 GB d03260db download
Qwen2.5-Coder-32B-Instruct-abliterated-v3.i1-IQ3_XXS.gguf 12.0 GB 229a26ab download
Q2_K 1 file 11.5 GB
Qwen2.5-Coder-32B-Instruct-abliterated-v3.i1-Q2_K.gguf 11.5 GB 255da014 download
IQ2 1 file 10.5 GB
Qwen2.5-Coder-32B-Instruct-abliterated-v3.i1-IQ2_M.gguf 10.5 GB 148626c3 download
Drafts and companions 1 file 28.6 MB
Qwen2.5-Coder-32B-Instruct-abliterated-v3.imatrix.gguf 28.6 MB 9cb27a4a download
Auxiliary files 2 files 2.69 KB
.gitattributes 2.21 KB c354c6a4 download
README.md 499 B 541d6242 download

README current version from Hugging Face

README history 4 versions

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

  1. 2026-11-12 auto-patch README.md d67f599 7.1 KB
    Loading...
  2. 2026-11-12 auto-patch README.md cc31e51 5.8 KB
    Loading...
  3. 2026-11-12 auto-patch README.md 63a6848 4 KB
    Loading...
  4. 2026-11-12 uploaded from rich1 7cb8392 499 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.

Open in Abliteration