Instructions to use lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M # Run inference directly in the terminal: llama cli -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M # Run inference directly in the terminal: llama cli -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M # Run inference directly in the terminal: ./llama-cli -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M
Use Docker
docker model run hf.co/lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M
- LM Studio
- Jan
- Ollama
How to use lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF with Ollama:
ollama run hf.co/lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M
- Unsloth Studio
How to use lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF to start chatting
- Atomic Chat new
- Docker Model Runner
How to use lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF with Docker Model Runner:
docker model run hf.co/lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M
- Lemonade
How to use lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Q3_K_M
Run and chat with the model
lemonade run user.Nidum-Gemma-3-27B-it-Uncensored-GGUF-Q3_K_M
List all available models
lemonade list
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:# Run inference directly in the terminal:
llama cli -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Use pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:# Run inference directly in the terminal:
./llama-cli -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Build from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:Use Docker
docker model run hf.co/lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:π§ Nidum Gemma-3-27B-Instruct Uncensored GGUF
At Nidum, we're committed to delivering powerful, versatile, and unrestricted AI experiences. The Nidum Gemma-3-27B-Instruct Uncensored GGUF collection provides quantized models optimized for efficient performance, enabling fast inference without compromising the quality of your interactions. Ideal for anyone seeking an open, uncensored AI experience with remarkable flexibility and accessibility.
π Why Choose Nidum Gemma-3-27B-Instruct Uncensored?
- Uncensored Experience: Engage openly, freely, and creatively without restrictive guardrails.
- Efficiency: Optimized quantization ensures high-quality responses at reduced computational costs.
- Versatility: Ideal for chatbots, creative writing, virtual assistants, education, research, and more.
- Community Driven: Built for users who value openness and innovation in AI interaction.
π₯ Download GGUF Models
We offer various GGUF quantized formats optimized for diverse needs. Choose the format that matches your desired balance between performance and efficiency:
| Model Version | Bits per Weight | Best For | Download Link |
|---|---|---|---|
| Q8_0 | 8-bit | Maximum accuracy and high performance | model-Q8_0.gguf |
| Q6_K | 6-bit | Excellent balance of speed and accuracy | model-Q6_K.gguf |
| Q5_K_M | ~5-bit | Balanced accuracy and lower memory usage | model-Q5_K_M.gguf |
| Q3_K_M | 3-bit | Good for limited hardware resources | model-Q3_K_M.gguf |
| TQ2_0 | Tiny 2-bit | Fast inference, minimal memory | model-TQ2_0.gguf |
| TQ1_0 | Tiny 1-bit | Extreme efficiency, minimal footprint | model-TQ1_0.gguf |
π Recommended Quantization:
- For top-quality applications: Use Q8_0 or Q6_K.
- Balanced accuracy & performance: Choose Q5_K_M.
- Mobile or hardware-constrained environments: Go with Q3_K_M, TQ2_0, or TQ1_0.
π Exciting Use Cases
- Creative Writing & Storytelling: Generate creative narratives and stories without limitations.
- Virtual Assistants: Provide unrestricted assistance and guidance.
- Educational Platforms: Engage students with open-ended questions and discussions.
- Research & Experimentation: Test boundary-pushing ideas without censorship.
- Interactive Fiction & Gaming: Create rich, immersive, and dynamic worlds.
π Experience AI Without Boundaries
With Nidum Gemma-3-27B-Instruct Uncensored GGUF, push the boundaries of what's possible. Discover limitless creativity, explore freely, and enjoy a genuinely uncensored AI interaction.
π Enjoy your unrestricted AI journey with Nidum!
- Downloads last month
- 515
1-bit
2-bit
3-bit
5-bit
6-bit
8-bit
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF:# Run inference directly in the terminal: llama cli -hf lemuralabs/Nidum-Gemma-3-27B-it-Uncensored-GGUF: