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

lemuralabs/Gemma-3-4B-it-Uncensored-GGUF

lemuralabs Gemma 4B GGUF 131K 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/lemuralabs%2FGemma-3-4B-it-Uncensored-GGUF"
Response includes
  • classification m-uncensored
  • files 11
  • hub_downloads_all_time 28,424
  • author_summary 31 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
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
28K
3K last 30d - cooling
Likes
13
Model age
19mo ago
created 2025-03-16
Downloads over time
Now30.4K→from25.5K↑19%
25.2K27.1K29K30.9K25.5K on Aug 530.4K on Oct 12AugSepOct
Aug 5 → Oct 12 · 51 snapshots · spans 68 days

Variants by this author 2 formats · 3K downloads combined

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

Metadata

License
gemma
Quantizations
F16 Q3_K Q5_K Q6_K Q8_0
Tags
gguf Uncensored license:gemma endpoints_compatible region:us conversational

Related

Total size
28.3 GB
Files
11
Quantizations
6
Registered
2026-08-22 13:56
Last updated on HF
2026-08-05 19:16

Files by quantization

F16 2 files 14.5 GB
Gemma-3-4B-it-Uncensored-F16.gguf 7.23 GB 635b1c05 download
nidum-gemma-3-4B-F16.gguf 7.23 GB 635b1c05 download
Q8_0 1 file 3.85 GB
model-Q8_0.gguf 3.85 GB 914171d9 download
Q6_K 1 file 2.97 GB
model-Q6_K.gguf 2.97 GB bf9df0b1 download
Q5_K 1 file 2.64 GB
model-Q5_K_M.gguf 2.64 GB d5e95ccf download
Q3_K 1 file 1.95 GB
model-Q3_K_M.gguf 1.95 GB 6b2d466e download
Auxiliary files 5 files 2.44 GB
model-TQ2_0.gguf 1.29 GB 3ac2e05c download
model-TQ1_0.gguf 1.15 GB 5607aa1e download
logo.png 18.6 KB a9400259 download
README.md 2.88 KB 1e2dc655 download
.gitattributes 1.92 KB d6881be7 download

README current version from Hugging Face


license: gemma
tags:

  • Uncensored

Lemura Labs

Lemura Labs Gemma-3-4B IT Uncensored GGUF

Format Params Type License

Welcome to Lemura Labs's Gemma-3-4B IT Uncensored GGUF, designed for creators, researchers, and AI enthusiasts looking for a powerful, versatile, and unrestricted AI experience. Our quantized models give you fast, efficient, and high-quality inference, empowering innovative use cases without limitations.

Why Choose Lemura Labs Gemma-3-4B IT Uncensored?

  • Unrestricted AI: No censorship—ideal for exploring creative and innovative ideas.
  • Efficiency & Speed: Optimized quantizations for rapid inference on diverse hardware.
  • Versatility: Excellent for creative writing, chatbot development, educational tools, personalized assistants, and more.
  • Open & Community-centric: Embrace the power of open, community-driven AI.

Available GGUF Models

Choose from multiple GGUF quantized formats tailored for your specific needs:

Quantization Description Bits per Weight Link
Q8_0 Best accuracy and excellent performance 8-bit model-Q8_0.gguf
Q6_K Strong accuracy, faster inference 6-bit model-Q6_K.gguf
Q5_K_M Ideal balance of speed & accuracy 5-bit model-Q5_K_M.gguf
Q3_K_M Memory-efficient with good performance 3-bit model-Q3_K_M.gguf
TQ2_0 Tiny quantization for maximum speed 2-bit model-TQ2_0.gguf
TQ1_0 Ultra-lightweight, minimal memory usage 1-bit model-TQ1_0.gguf

Recommended Quantization Usage:

  • Highest Quality & Performance: Q8_0 or Q6_K
  • Balanced Approach: Q5_K_M
  • Low-resource Environments (mobile, edge): Q3_K_M, TQ2_0, or TQ1_0

Use-Cases & Applications

Explore limitless AI use-cases with Lemura Labs Gemma-3-4B IT Uncensored GGUF:

  • Creative Content Generation: Stories, scripts, poetry, and art.
  • Virtual Assistants: Natural, open-ended conversations.
  • Educational Purposes: Enhanced, unrestricted learning interactions.
  • Interactive Entertainment: Rich storytelling and immersive role-play.
  • Research and Innovation: Test new ideas and hypotheses without censorship.

Unleash Your Creativity with Lemura Labs

Dive in today and experience an uncensored, fast, and powerful AI journey tailored for open-minded creators, innovators, and AI enthusiasts!

Enjoy your uncensored AI experience with Lemura Labs!

README history 1 version

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

  1. 2026-08-05Initial commit3051c652.9 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.

Open in Abliteration