Instructions to use RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF",
	filename="12B Gemma 3 IT norm preserved biprojected abliterated Q2KS.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF
# Run inference directly in the terminal:
llama-cli -hf RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF
# Run inference directly in the terminal:
llama-cli -hf RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-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 RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF
# Run inference directly in the terminal:
./llama-cli -hf RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-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 RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF

Use Docker

docker model run hf.co/RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF

LM Studio
Jan
Ollama
How to use RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF with Ollama:
```
ollama run hf.co/RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF
```

Unsloth Studio

How to use RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-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 RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-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 RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF to start chatting

Docker Model Runner
How to use RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF
```

Lemonade

How to use RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RossAscends/grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF

Run and chat with the model

lemonade run user.grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

grimjim-12B-Gemma-3-it-norm-preserved-biprojected-abliterated-GGUF / README.md

RossAscends

Update README.md

a94af04 verified 7 months ago

422 Bytes

license: mit
base_model:
  - grimjim/gemma-3-12b-it-norm-preserved-biprojected-abliterated

GGUF quants of: https://huggingface.co/grimjim/gemma-3-12b-it-norm-preserved-biprojected-abliterated

Ctx limits per quant (RTX 3060 12GB, F16 k/v, no offload):

quant	ctx
Q2_K_S	16k
iQ3_S	15k
Q3_K_S	15k
iQ4_XS	12k
iQ4_NL	10k (16k with q8_0 k/v)
Q4_K_S	10k ( " )
Q5_K_S	8k (15k with q8_0 k/v)