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

szili2011/Qwen3-0.6B-Opus4.6-Abliterated-GGUF

szili2011 Qwen 600M GGUF 41K 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/szili2011%2FQwen3-0.6B-Opus4.6-Abliterated-GGUF"
Response includes
  • classification m8
  • files 12
  • hub_downloads_all_time 3,893
  • author_summary 1 models
  • readme_text full
Try next
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
374 last 30d - cooling
Likes
3
Model age
6mo ago
created 2026-04-08
Downloads over time
Now4K→from2.1K↑91%
2K2.7K3.4K4.1K2.1K on Apr 224K on Oct 12AprMayJunJulAugSepOct
Apr 22 → Oct 12 · 65 snapshots · spans 173 days

Metadata

License
apache-2.0
Quantizations
BF16 F16 IQ4 Q2_K Q3_K Q4 Q4_K Q5_K Q6_K Q8_0
Tags
gguf license:apache-2.0 endpoints_compatible region:us conversational
Total size
5.37 GB
Files
12
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2026-04-24 17:15
Source huggingface.co/szili2011/Qwen3-0.6B-Opus4.6-Abliterated-GGUF ↗

Files by quantization

BF16 1 file 1.12 GB
qwenpus0.6B-bf16.gguf 1.12 GB d4b7ebbf download
F16 1 file 1.12 GB
qwenpus0.6B-f16.gguf 1.12 GB 3d82a209 download
Q8_0 1 file 610 MB
qwenpus0.6B-Q8_0.gguf 610 MB 01177d5c download
Q6_K 1 file 472 MB
qwenpus0.6B-Q6_K.gguf 472 MB e6343a82 download
Q5_K 1 file 424 MB
qwenpus0.6B-Q5_K_M.gguf 424 MB 19e9a2b6 download
Q4_K 1 file 378 MB
qwenpus0.6B-Q4_K_M.gguf 378 MB 384dd0f7 download
Q4 1 file 364 MB
qwenpus0.6B-Q4_0.gguf 364 MB b4151a99 download
IQ4 1 file 352 MB
qwenpus0.6B-IQ4_XS.gguf 352 MB 38fe2deb download
Q3_K 1 file 331 MB
qwenpus0.6B-Q3_K_M.gguf 331 MB cde4e712 download
Q2_K 1 file 283 MB
qwenpus0.6B-Q2_K.gguf 283 MB 3348da55 download
Auxiliary files 2 files 2.78 KB
.gitattributes 2.57 KB bf22c26b download
README.md 216 B 68950fcf download

README current version from Hugging Face

license: apache-2.0

The Qwen3 model was fine-tuned using the Opus 4.6 reasoning dataset,
with a focus on enhancing multi-step inference, logical consistency, and
instruction following across complex tasks.

README history 4 versions

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

  1. 2026-04-24Update README.mdbe92432216 B
    Loading...
  2. 2026-04-08Update README.md2d86a1e218 B
    Loading...
  3. 2026-04-08Update README.mdb1c799799 B
    Loading...
  4. 2026-04-08initial commitf785c9028 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