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

cgus/Qwen2-1.5B-Instruct-Abliterated-iMat-GGUF

cgus Qwen 1.5B GGUF second-order 33K 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/cgus%2FQwen2-1.5B-Instruct-Abliterated-iMat-GGUF"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 3,914
  • author_summary 13 models
  • readme_text full
Try next
GET/models?author=cgus
All 13 models by cgus
 GET/models?family=qwen&method=m8
Sibling qwen 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
4K
195 last 30d - cooling
Likes
1
Model age
2.3y ago
created 2024-06-16
Downloads over time
Now4K→from63↑6,213%
01.5K2.9K4.4K63 on Jul 24, 20244K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 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.

trollek/Qwen2-1.5B-Instruct-Abliterated↓ 35 this lineage
cgus/Qwen2-1.5B-Instruct-Abliterated-iMat-GGUF↓ 195

Metadata

License
apache-2.0
Quantizations
F32 IQ2 IQ3 Q4 Q4_K Q5_K Q6_K Q8_0
Tags
gguf not-for-all-audiences base_model:trollek/Qwen2-1.5B-Instruct-Abliterated base_model:quantized:trollek/Qwen2-1.5B-Instruct-Abliterated license:apache-2.0 region:us conversational

Related

Other by cgus
Qwen2-7B-Instruct-abliterated-iMat-GGUF 214 Huihui-Qwen3-14B-abliterated-v2-exl2 57 Qwen2.5-14B-Instruct-abliterated-v2-exl2 37 Qwen2-7B-Instruct-abliterated-exl2 35 Josiefied-Qwen3-8B-abliterated-v1-exl2 27
Same base model
mradermacher/Qwen2-1.5B-Instruct-Abliterated-i1-GGUF 392 mradermacher/Qwen2-1.5B-Instruct-Abliterated-GGUF 310 cgus/Qwen2-1.5B-Instruct-abliterated-exl2 21
Total size
14.3 GB
Files
13
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2024-12-16 23:00
Source huggingface.co/cgus/Qwen2-1.5B-Instruct-Abliterated-iMat-GGUF ↗ Base model trollek/Qwen2-1.5B-Instruct-Abliterated →

Files by quantization

F32 1 file 5.76 GB
Qwen2-1.5B-Instruct-Abliterated-FP32.gguf 5.76 GB b7cac8a6 download
Q8_0 1 file 1.53 GB
Qwen2-1.5B-Instruct-Abliterated-Q8_0.gguf 1.53 GB 7ede3074 download
Q6_K 1 file 1.19 GB
Qwen2-1.5B-Instruct-Abliterated-Q6_K.gguf 1.19 GB 6cb616ac download
Q5_K 1 file 1.05 GB
Qwen2-1.5B-Instruct-Abliterated-Q5_K_M.gguf 1.05 GB d19e8680 download
Q4_K 1 file 940 MB
Qwen2-1.5B-Instruct-Abliterated-Q4_K_M.gguf 940 MB 71df1494 download
Q4 3 files 2.61 GB
Qwen2-1.5B-Instruct-Abliterated-Q4_0_4_4.gguf 892 MB 99627bbf download
Qwen2-1.5B-Instruct-Abliterated-Q4_0_4_8.gguf 892 MB f0f4a327 download
Qwen2-1.5B-Instruct-Abliterated-Q4_0_8_8.gguf 892 MB 9fd1d7c3 download
IQ3 1 file 741 MB
Qwen2-1.5B-Instruct-Abliterated-IQ3_M.gguf 741 MB 564b51ef download
IQ2 1 file 573 MB
Qwen2-1.5B-Instruct-Abliterated-IQ2_M.gguf 573 MB de085fae download
Auxiliary files 3 files 1.95 MB
Qwen2-1.5B-Instruct-Abliterated-imatrix.dat 1.95 MB 0485da67 download
.gitattributes 2.34 KB 9591dab0 download
README.md 1.50 KB 9409523a download

README current version from Hugging Face

license: apache-2.0
inference: false
tags:

  • not-for-all-audiences
    base_model: trollek/Qwen2-1.5B-Instruct-Abliterated

Qwen2-1.5B-Instruct-Abliterated-GGUF

Model: Qwen2-1.5B-Instruct-Abliterated
Made by: trollek

Based on original model: Qwen2-1.5B-Instruct
Created by: Qwen

Quantization notes

Made with llama.cpp-b3154 with imatrix file based on Exllamav2 default dataset.
01.09.2024: Added Q4_0_4_4 (low end ARM CPUs), Q4_0_4_8 and Q4_0_8_8 (high end ARM CPUs).
On my PC with i7-3770 CPU these are significantly slower than Q4_K_M.
On my phone Q4_0_4_4 is marginally faster than Q4_K_M.
17.12.2024: Readme update. It seems Q4_0_4_4, Q4_0_4_8 and Q4_0_8_8 support was removed in recent llama.cpp. I'll keep them but they might be no longer useful.

Original model card

This is an abliterated version of Qwen2-1.5B-Instruct using the same procedure as augmxnt/Qwen2-7B-Instruct-deccp with their code on Github with some added lines from mlabonne/harmful_behaviors to the harmful.txt file.

I have not done anything else to the model. Yet.

README history 5 versions

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

  1. 2024-12-16Update README.mdf680df81.5 KB
    Loading...
  2. 2024-09-01Update README.md6bfef231.3 KB
    Loading...
  3. 2024-09-01Update README.md17efb2b1.3 KB
    Loading...
  4. 2024-09-01Update README.md94e506f1.3 KB
    Loading...
  5. 2024-06-16Create README.mde3bcf631.1 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