Instructions to use blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S",
	filename="llama-sahabat-70b-Q2_K_S.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S 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 blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S
# Run inference directly in the terminal:
llama cli -hf blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S
# Run inference directly in the terminal:
llama cli -hf blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S

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 blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S
# Run inference directly in the terminal:
./llama-cli -hf blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S

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 blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S

Use Docker

docker model run hf.co/blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S

LM Studio
Jan
Ollama
How to use blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S with Ollama:
```
ollama run hf.co/blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S
```

Unsloth Studio

How to use blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S 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 blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S 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 blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S to start chatting

Atomic Chat new
Docker Model Runner
How to use blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S with Docker Model Runner:
```
docker model run hf.co/blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S
```

Lemonade

How to use blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S:Q2_K_S

Run and chat with the model

lemonade run user.Llama-Sahabat-AI-v2-70B-IT-Q2_K_S-Q2_K_S

List all available models

lemonade list

Llama-Sahabat-AI-v2-70B-IT - Q2_K_S GGUF

Quantized GGUF version of Sahabat-AI/Llama-Sahabat-AI-v2-70B-IT.

About the base model

Sahabat-AI adalah model bahasa besar (LLM) yang dikembangkan secara kolaboratif oleh BRIN, GoTo, dan Bukalapak untuk mendukung ekosistem AI berbahasa Indonesia. Model ini dilatih menggunakan data bahasa Indonesia yang kaya dan beragam, sehingga mampu memahami konteks budaya, bahasa, dan kebutuhan spesifik pengguna Indonesia dengan lebih baik.

Sahabat AI is a Large Language Model (LLM) collaboratively developed by BRIN (National Research and Innovation Agency), GoTo, and Bukalapak to support the Indonesian-language AI ecosystem. Trained on rich and diverse Indonesian language data, it better understands the cultural context, language nuances, and specific needs of Indonesian users.

Quantization details

Property	Value
Quantization	Q2_K_S
Bits per weight	2.77 BPW
File size	~23 GB
Original size	~141 GB (bf16)
imatrix	Yes (generated from Q3_K_S with groups_merged.txt calibration data)

Note: Q2_K_S is the most aggressive quantization — expect noticeable quality degradation vs Q3_K_S or Q8_0. Use Q3_K_S for better quality or Q8_0 for near-lossless inference.

Other quantizations

techhermit/Llama-Sahabat-AI-v2-70B-IT-Q3_K_S — 29 GB, 3.50 BPW
techhermit/Llama-Sahabat-AI-v2-70B-IT-Q8_0 — 70 GB, 8.50 BPW (near-lossless)

Usage

Load with any llama.cpp-compatible runner (llama.cpp, ollama, LM Studio, etc.):

llama-cli -m llama-sahabat-70b-Q2_K_S.gguf -p "Halo, apa kabar?"

Downloads last month: 7

GGUF

Model size

71B params

Architecture

llama

Hardware compatibility

2-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for blackshell69/Llama-Sahabat-AI-v2-70B-IT-Q2_K_S

Base model

Sahabat-AI/Llama-Sahabat-AI-v2-70B-IT

Quantized

(4)

this model