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

Novaciano/Gemma3-UNCENSORED-1B-GGUF

Novaciano Gemma 1B 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/Novaciano%2FGemma3-UNCENSORED-1B-GGUF"
Response includes
  • classification m5
  • files 8
  • hub_downloads_all_time 1,175
  • author_summary 60 models
  • readme_text full
Try next
GET/models?author=Novaciano
All 60 models by Novaciano
 GET/models?family=gemma&method=m5
Sibling gemma models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

No other method signals detected in this model.
Confidence
MEDIUM
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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • no abliteration marker
How we label → About M5 →
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
1K
152 last 30d - stable
Likes
0
Model age
10mo ago
created 2025-11-20
Downloads over time
Now1.2K→from238↑416%
1885689481.3K238 on Nov 19, 20251.2K on Oct 111.2K on Oct 10Nov '25JanMarMayJulSep
Nov 19, 2025 → Oct 11 · 86 snapshots · spans 326 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.

Novaciano/Gemma3-UNCENSORED-1B↓ 22 this lineage
Novaciano/Gemma3-UNCENSORED-1B-GGUF↓ 152

Variants by this author 2 formats · 174 downloads combined

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

Metadata

Quantizations
Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf mergekit merge llama-cpp gguf-my-repo base_model:Novaciano/Gemma3-UNCENSORED-1B base_model:quantized:Novaciano/Gemma3-UNCENSORED-1B endpoints_compatible region:us

Related

Other by Novaciano
Llama-3.2-3b-NSFW_Aesir_Uncensored-GGUF 2K Llama-3.2_1b_Uncensored_RP_Aesir_GGUF 2K Uncensored-1b-Creative_Writing_RP-GGUF 1K DOLPHIN3.0-L3.2-1B_RP_UNCENSORED-GGUF 1K Qwen2.5_Uncensored_V2_Sexting-GGUF 637
Same base model
mradermacher/Gemma3-UNCENSORED-1B-GGUF 1K mradermacher/Gemma3-UNCENSORED-1B-i1-GGUF 1K Novaciano/Gemma3-ToxiCity_Uncensored-1B 12
Total size
5.15 GB
Files
8
Quantizations
6
Registered
2026-08-22 13:56
Last updated on HF
2025-11-20 06:45
Source huggingface.co/Novaciano/Gemma3-UNCENSORED-1B-GGUF ↗ Base model Novaciano/Gemma3-UNCENSORED-1B →

Files by quantization

Q8_0 1 file 1020 MB
Gemma3-UNCENSORED-1B-Q8_0.gguf 1020 MB d53c7e37 download
Q6_K 1 file 965 MB
Gemma3-UNCENSORED-1B-Q6_K.gguf 965 MB 3f084c53 download
Q5_K 1 file 812 MB
Gemma3-UNCENSORED-1B-Q5_K_M.gguf 812 MB d214fb10 download
Q4_K 1 file 769 MB
Gemma3-UNCENSORED-1B-Q4_K_M.gguf 769 MB 49d11c9d download
Q3_K 1 file 689 MB
Gemma3-UNCENSORED-1B-Q3_K_M.gguf 689 MB fbd9d0f6 download
Auxiliary files 3 files 1020 MB
Gemma3-UNCENSORED-1B-MXFP4_MOE.gguf 1020 MB 099aefa4 download
.gitattributes 1.89 KB 80d57147 download
README.md 1.06 KB 9aef0301 download

README current version from Hugging Face

base_model: Novaciano/Gemma3-UNCENSORED-1B
library_name: transformers
tags:

  • mergekit
  • merge
  • llama-cpp
  • gguf-my-repo

Gemma3-UNCENSORED-1B

Model creator: Novaciano

Original model: Novaciano/Gemma3-UNCENSORED-1B

GGUF quantization: provided by Novaciano using llama.cpp

Special thanks

🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.

Use with Ollama

ollama run "hf.co/Novaciano/Gemma3-UNCENSORED-1B-GGUF:MXFP4_MOE"

Use with LM Studio

lms load "Novaciano/Gemma3-UNCENSORED-1B-GGUF"

Use with llama.cpp CLI

llama-cli --hf "Novaciano/Gemma3-UNCENSORED-1B-GGUF:MXFP4_MOE" -p "The meaning to life and the universe is"

Use with llama.cpp Server:

llama-server --hf "Novaciano/Gemma3-UNCENSORED-1B-GGUF:MXFP4_MOE" -c 4096

README history 6 versions

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

  1. 2025-11-20Upload README.md with huggingface_hubbed3db81.1 KB
    Loading...
  2. 2025-11-20Upload README.md with huggingface_hub033b79e1 KB
    Loading...
  3. 2025-11-20Upload README.md with huggingface_hub89421831 KB
    Loading...
  4. 2025-11-20Upload README.md with huggingface_hub52c71751 KB
    Loading...
  5. 2025-11-20Upload README.md with huggingface_hubc30e4fd1 KB
    Loading...
  6. 2025-11-20Upload README.md with huggingface_hubeb46eea1 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