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

arzaan789/smolm2-1.7b-uncensored

arzaan789 1.7B GGUF 8K 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%2Fsmolm2-1.7b-uncensored"
Response includes
  • classification m8
  • files 13
  • benchmarks 5 entries
  • hub_downloads_all_time 2,266
  • 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
2K
628 last 30d - stable
Likes
2
Model age
6mo ago
created 2026-04-06
Downloads over time
Now2.4K→from297↑718%
1901K1.8K2.6K297 on Apr 152.4K on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 66 snapshots · spans 179 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Arena-Battles 2375 LM-Arena
LM Arena Elo 1062.298401200184 LM-Arena
Arena-Elo-Lower 1048.9593756268487 LM-Arena
Arena-Elo-Upper 1075.6374267735189 LM-Arena
Arena-Rank 206 LM-Arena

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/SmolLM2-1.7B-Instruct this lineage
arzaan789/smolm2-1.7b-uncensored↓ 628

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/SmolLM2-1.7B-Instruct base_model:quantized:HuggingFaceTB/SmolLM2-1.7B-Instruct 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
Same base model
ElementMerc/smollm2-1.7b-abliterated 286 ops-malware/smollm2-1.7b-abliterated 264 thirdeyeai/SmolLM2-1.7B-Instruct-Uncensored 44
Total size
13.4 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-04-06 06:32
Source huggingface.co/arzaan789/smolm2-1.7b-uncensored ↗ Base model HuggingFaceTB/SmolLM2-1.7B-Instruct ↗

Files by quantization

F16 1 file 3.19 GB
smolm2_1.7b_uncensored.f16.gguf 3.19 GB 25555363 download
Q8_0 1 file 1.70 GB
smolm2_1.7b_uncensored.Q8_0.gguf 1.70 GB 44883369 download
Q6_K 1 file 1.31 GB
smolm2_1.7b_uncensored.Q6_K.gguf 1.31 GB 4ee0e78b download
Q5_K 2 files 2.25 GB
smolm2_1.7b_uncensored.Q5_K_M.gguf 1.14 GB 1be66a9b download
smolm2_1.7b_uncensored.Q5_K_S.gguf 1.11 GB 002a16a3 download
Q4_K 2 files 1.91 GB
smolm2_1.7b_uncensored.Q4_K_M.gguf 1007 MB f02164de download
smolm2_1.7b_uncensored.Q4_K_S.gguf 953 MB ba97f0ad download
Q3_K 3 files 2.39 GB
smolm2_1.7b_uncensored.Q3_K_L.gguf 889 MB a53db2d6 download
smolm2_1.7b_uncensored.Q3_K_M.gguf 820 MB 27d6012f download
smolm2_1.7b_uncensored.Q3_K_S.gguf 741 MB 7783bc97 download
Q2_K 1 file 643 MB
smolm2_1.7b_uncensored.Q2_K.gguf 643 MB 574a8182 download
Auxiliary files 2 files 3.54 KB
.gitattributes 2.24 KB 68c43475 download
README.md 1.31 KB 2f051ef2 download

README current version from Hugging Face

license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
tags:

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

smolm2-1.7b-uncensored

Uncensored variant of HuggingFaceTB/SmolLM2-1.7B-Instruct.

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) 7/64

Usage

llama-cli -m smolm2_1.7b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model HuggingFaceTB/SmolLM2-1.7B-Instruct
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_hub56afa891.3 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