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

Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-gguf

Goekdeniz-Guelmez Qwen 500M 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/Goekdeniz-Guelmez%2FJosiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-gguf"
Response includes
  • classification m8
  • files 17
  • hub_downloads_all_time 5,958
  • author_summary 44 models
  • readme_text full
Try next
GET/models?author=Goekdeniz-Guelmez
All 44 models by Goekdeniz-Guelmez
 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
6K
511 last 30d - cooling
Likes
1
Model age
23mo ago
created 2024-11-17
Downloads over time
Now6.1K→from281↑2,075%
02.2K4.5K6.7K281 on Nov 13, 20246.1K on Oct 11Nov '24Feb '25May '25Aug '25Nov '25FebMayAug
Nov 13, 2024 → Oct 11 · 139 snapshots · spans 697 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.

Goekdeniz-Guelmez/Josiefied-Qwen2-0.5B-Instruct-abliterated↓ 41 this lineage
Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-gguf↓ 511

Variants by this author 2 formats · 646 downloads combined

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

Metadata

License
apache-2.0
Quantizations
F16 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0
Tags
gguf chat GGUF text-generation base_model:Goekdeniz-Guelmez/Josiefied-Qwen2-0.5B-Instruct-abliterated base_model:quantized:Goekdeniz-Guelmez/Josiefied-Qwen2-0.5B-Instruct-abliterated license:apache-2.0 endpoints_compatible region:us conversational

Related

Other by Goekdeniz-Guelmez
Josiefied-Qwen2.5-Coder-14B-Instruct-abliterated-v1 9K Josiefied-Qwen2-1.5B-Instruct-abliterated-gguf 3K Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-gguf 2K Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-gguf 2K Josiefied-Qwen3-8B-abliterated-v1 2K
Same base model
mradermacher/Josiefied-Qwen2-0.5B-Instruct-abliterated-GGUF 270 mradermacher/Josiefied-Qwen2-0.5B-Instruct-abliterated-i1-GGUF 262
Total size
7.64 GB
Files
17
Quantizations
10
Registered
2026-08-22 13:56
Last updated on HF
2025-03-07 18:40
Source huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-gguf ↗ Base model Goekdeniz-Guelmez/Josiefied-Qwen2-0.5B-Instruct-abliterated →

Files by quantization

F16 1 file 1.18 GB
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.fp16.bin 1.18 GB 5e9206a0 download
Q8_0 1 file 644 MB
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q8_0.gguf 644 MB 561c9c16 download
Q6_K 1 file 620 MB
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q6_K.gguf 620 MB 6349b679 download
Q5_K 2 files 989 MB
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q5_K_M.gguf 498 MB 292a0b9e download
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q5_K_S.gguf 491 MB f3f297f1 download
Q5 2 files 965 MB
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q5_1.gguf 497 MB 3abd7f2e download
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q5_0.gguf 468 MB ba73a760 download
Q4_K 2 files 926 MB
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q4_K_M.gguf 469 MB 57a7ec65 download
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q4_K_S.gguf 457 MB aa73db92 download
Q4 2 files 847 MB
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q4_1.gguf 438 MB 5490cb27 download
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q4_0.gguf 409 MB 6673d8cb download
Q3_K 3 files 1.20 GB
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q3_K_L.gguf 425 MB d4205f61 download
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q3_K_M.gguf 412 MB a50351fc download
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q3_K_S.gguf 396 MB 94467c1c download
Q2_K 1 file 396 MB
josiefied-qwen2.5-0.5b-instruct-abliterated-v1.Q2_K.gguf 396 MB d1dbe477 download
Auxiliary files 2 files 3.46 KB
.gitattributes 2.77 KB 2e25a9cd download
README.md 706 B 7890183b download

README current version from Hugging Face

license: apache-2.0
tags:

  • chat
  • GGUF
    base_model: Goekdeniz-Guelmez/Josiefied-Qwen2-0.5B-Instruct-abliterated
    pipeline_tag: text-generation

Model Card for Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-gguf

Model Description

This is the GGUF Quantisationn of Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1.

ollama run goekdenizguelmez/JOSIEFIED-Qwen2.5:0.5b

  • Developed by: Gökdeniz Gülmez
  • Funded by: Gökdeniz Gülmez
  • Shared by: Gökdeniz Gülmez
  • Origional model: Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1

README history 2 versions

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

  1. 2025-03-07Update README.md269f2b8706 B
    Loading...
  2. 2024-11-17Rename README_GGUF.md to README.md4042bcd652 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