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

arzaan789/smolm3-3b-uncensored

arzaan789 3B GGUF 66K 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%2Fsmolm3-3b-uncensored"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 2,637
  • author_summary 28 models
  • readme_text full
Try next
GET/models?author=arzaan789
All 28 models by arzaan789
 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
3K
878 last 30d - stable
Likes
0
Model age
6mo ago
created 2026-04-05
Downloads over time
Now2.8K→from335↑721%
2141.1K2.1K3K335 on Apr 152.8K 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.

HuggingFaceTB/SmolLM3-3B this lineage
arzaan789/smolm3-3b-uncensored↓ 878

Metadata

License
apache-2.0
Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf uncensored abliterated smollm conversational text-generation base_model:HuggingFaceTB/SmolLM3-3B base_model:quantized:HuggingFaceTB/SmolLM3-3B 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 qwen2.5-0.5b-uncensored 798
Same base model
richardyoung/SmolLM3-3B-abliterated-obliteratus 458 mlx-community/SmolLM3-3B-abliterated-bf16 42 vpakarinen/smollm3-3b-uncensored-thinking 26
Total size
24.2 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-04-05 22:21
Source huggingface.co/arzaan789/smolm3-3b-uncensored ↗ Base model HuggingFaceTB/SmolLM3-3B ↗

Files by quantization

F16 1 file 5.74 GB
smolm3_3b_uncensored.f16.gguf 5.74 GB a8a56230 download
Q8_0 1 file 3.05 GB
smolm3_3b_uncensored.Q8_0.gguf 3.05 GB 4e1584f5 download
Q6_K 1 file 2.36 GB
smolm3_3b_uncensored.Q6_K.gguf 2.36 GB f2831bba download
Q5_K 2 files 4.07 GB
smolm3_3b_uncensored.Q5_K_M.gguf 2.06 GB eb785274 download
smolm3_3b_uncensored.Q5_K_S.gguf 2.01 GB e6281835 download
Q4_K 2 files 3.48 GB
smolm3_3b_uncensored.Q4_K_M.gguf 1.78 GB 601ffb92 download
smolm3_3b_uncensored.Q4_K_S.gguf 1.69 GB f15877e8 download
Q3_K 3 files 4.37 GB
smolm3_3b_uncensored.Q3_K_L.gguf 1.57 GB 51d75ffd download
smolm3_3b_uncensored.Q3_K_M.gguf 1.46 GB 62aeea9d download
smolm3_3b_uncensored.Q3_K_S.gguf 1.33 GB 6a92757b download
Q2_K 1 file 1.17 GB
smolm3_3b_uncensored.Q2_K.gguf 1.17 GB 3e84b15d download
Auxiliary files 2 files 3.48 KB
.gitattributes 2.22 KB d827dc27 download
README.md 1.26 KB d4c9a803 download

README current version from Hugging Face

license: apache-2.0
base_model: HuggingFaceTB/SmolLM3-3B
tags:

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

smolm3-3b-uncensored

Uncensored variant of HuggingFaceTB/SmolLM3-3B.

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) 1/64
Harmless (64 prompts) 0/64

Usage

llama-cli -m smolm3_3b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model HuggingFaceTB/SmolLM3-3B
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. 2026-04-05Upload README.md with huggingface_huba0d33d01.3 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