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

arzaan789/stablelm-2-1.6b-uncensored

arzaan789 Sd 1.6B GGUF 4K 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/arzaan789%2Fstablelm-2-1.6b-uncensored"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 1,592
  • author_summary 28 models
  • readme_text full
Try next
GET/models?author=arzaan789
All 28 models by arzaan789
 GET/models?family=sd&method=m8
Sibling sd 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
2K
303 last 30d - stable
Likes
0
Model age
6mo ago
created 2026-04-06
Downloads over time
Now1.7K→from280↑501%
2107481.3K1.8K280 on Apr 151.7K on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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.

stabilityai/stablelm-2-1_6b-chat this lineage
arzaan789/stablelm-2-1.6b-uncensored↓ 303

Metadata

License
apache-2.0
Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf uncensored abliterated stablelm conversational text-generation base_model:stabilityai/stablelm-2-1_6b-chat base_model:quantized:stabilityai/stablelm-2-1_6b-chat license:apache-2.0 endpoints_compatible region:us

Related

Other by arzaan789
phi-4-mini-uncensored 1K qwen2.5-1.5b-uncensored 1K qwen2.5-3b-uncensored 1K qwen3.5-4b-uncensored 907 smolm3-3b-uncensored 878
Total size
13.1 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-04-06 00:53
Source huggingface.co/arzaan789/stablelm-2-1.6b-uncensored ↗ Base model stabilityai/stablelm-2-1_6b-chat ↗

Files by quantization

F16 1 file 3.07 GB
stablelm_2_1.6b_uncensored.f16.gguf 3.07 GB fc1ae291 download
Q8_0 1 file 1.63 GB
stablelm_2_1.6b_uncensored.Q8_0.gguf 1.63 GB b20aef13 download
Q6_K 1 file 1.26 GB
stablelm_2_1.6b_uncensored.Q6_K.gguf 1.26 GB 7215aad6 download
Q5_K 2 files 2.19 GB
stablelm_2_1.6b_uncensored.Q5_K_M.gguf 1.11 GB 269ebbf3 download
stablelm_2_1.6b_uncensored.Q5_K_S.gguf 1.08 GB 2befcbf5 download
Q4_K 2 files 1.88 GB
stablelm_2_1.6b_uncensored.Q4_K_M.gguf 984 MB 95c3238a download
stablelm_2_1.6b_uncensored.Q4_K_S.gguf 943 MB c6968d8b download
Q3_K 3 files 2.39 GB
stablelm_2_1.6b_uncensored.Q3_K_L.gguf 873 MB aa410835 download
stablelm_2_1.6b_uncensored.Q3_K_M.gguf 818 MB aa7f06cd download
stablelm_2_1.6b_uncensored.Q3_K_S.gguf 755 MB c49ccbd4 download
Q2_K 1 file 662 MB
stablelm_2_1.6b_uncensored.Q2_K.gguf 662 MB c65dccc3 download
Auxiliary files 2 files 3.59 KB
.gitattributes 2.28 KB bf36c72a download
README.md 1.31 KB 94dc3ba9 download

README current version from Hugging Face

license: apache-2.0
base_model: stabilityai/stablelm-2-1_6b-chat
tags:

  • uncensored
  • abliterated
  • gguf
  • stablelm
  • conversational
    pipeline_tag: text-generation

stablelm-2-1.6b-uncensored

Uncensored variant of stabilityai/stablelm-2-1_6b-chat.

Method

  1. Abliteration (strength=0.2) — refusal direction removed from all layers
  2. LoRA fine-tune on Guilherme34/uncensor (2 epochs, r=16, alpha=32)
  3. Re-abliteration (strength=0.35) — stronger pass to remove residual refusals

Eval Results

Split Refused
Harmful (64 prompts) 0/64
Harmless (64 prompts) 1/64

Usage

llama-cli -m stablelm_2_1.6b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model stabilityai/stablelm-2-1_6b-chat
Fine-tune Dataset Guilherme34/uncensor
Epochs 2
LoRA r 16
LoRA alpha 32
Learning Rate 0.0002
Abliteration Strength 0.2
Re-abliteration Strength 0.35

Credits

README history 1 version

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

  1. 2026-04-06Upload README.md with huggingface_hub91dfeb91.3 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