Instructions to use agbalu/Jugurtha-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use agbalu/Jugurtha-4B-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 agbalu/Jugurtha-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf agbalu/Jugurtha-4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf agbalu/Jugurtha-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf agbalu/Jugurtha-4B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf agbalu/Jugurtha-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf agbalu/Jugurtha-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/agbalu/Jugurtha-4B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use agbalu/Jugurtha-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "agbalu/Jugurtha-4B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "agbalu/Jugurtha-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/agbalu/Jugurtha-4B-GGUF:Q4_K_M

Ollama
How to use agbalu/Jugurtha-4B-GGUF with Ollama:
```
ollama run hf.co/agbalu/Jugurtha-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use agbalu/Jugurtha-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agbalu/Jugurtha-4B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "agbalu/Jugurtha-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use agbalu/Jugurtha-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/agbalu/Jugurtha-4B-GGUF:Q4_K_M
```

Lemonade

How to use agbalu/Jugurtha-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull agbalu/Jugurtha-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Jugurtha-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use agbalu/Jugurtha-4B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agbalu/Jugurtha-4B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default agbalu/Jugurtha-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use agbalu/Jugurtha-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agbalu/Jugurtha-4B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "agbalu/Jugurtha-4B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Jugurtha-4B (GGUF)

Quantized GGUF weights for Jugurtha-4B, the first instruction-tuned foundation model for Kabyle (Taqbaylit, kab, Latin script) with native chain-of-thought reasoning.

Optimized for consumer hardware, edge devices, LM Studio, and Ollama.

Provided Quantizations

File	Size	Format	Description
`Jugurtha-4B-Q4_K_M.gguf`	2.6 GB	Q4_K_M	Recommended. Balanced 4-bit quant; fits on 8 GB+ laptops with peak speed. Default for Ollama.
`Jugurtha-4B-Q5_K_M.gguf`	3.0 GB	Q5_K_M	High precision. 5-bit quant; recommended for complex reasoning on 16 GB+ systems.
`Jugurtha-4B-Q8_0.gguf`	4.3 GB	Q8_0	Near-lossless. 8-bit quant; identical benchmark accuracy to BF16.

Direct Usage with Ollama

Run directly from Hugging Face without manual downloads:

# Direct fast responses (Thinking OFF)
ollama run hf.co/agbalu/Jugurtha-4B-GGUF --think=false

# Full Chain-of-Thought reasoning in Taqbaylit (Thinking ON)
ollama run hf.co/agbalu/Jugurtha-4B-GGUF --think=true

Inside an interactive Ollama session, you can toggle thinking at any time:

/set nothink — immediate, concise answers
/set think — detailed internal reasoning in Taqbaylit

Direct Usage with LM Studio

Open LM Studio.
Search for agbalu/Jugurtha-4B-GGUF.
Choose your quantization (Q4_K_M recommended) and click Download.
Click Load Model. Ensure GPU Offload is set to Max for peak speed (40–70 tok/s on Apple Silicon / CUDA).
Toggle the Thinking / Reasoning switch in the sidebar to turn reasoning on or off.

Direct Usage with llama.cpp

For fast multi-threaded GPU inference:

# Thinking OFF (direct answer)
llama-cli -m Jugurtha-4B-Q4_K_M.gguf -ngl 99 -t 8 \
    -p "<|im_start|>user\nSegzi-yi-d s wegzul d acu i d Agbalu.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n" \
    -n 512

# Thinking ON (chain-of-thought in Taqbaylit)
llama-cli -m Jugurtha-4B-Q4_K_M.gguf -ngl 99 -t 8 \
    -p "<|im_start|>user\nAcḥal i d 25 x 4?<|im_end|>\n<|im_start|>assistant\n<think>\n" \
    -n 512

Main Model & Details

For full model benchmarks, training recipe, and architecture details, refer to the main repository: agbalu/Jugurtha-4B.

Licence

Apache-2.0

Downloads last month: 442

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

8-bit

Model tree for agbalu/Jugurtha-4B-GGUF

Base model

agbalu/Jugurtha-4B

Quantized

(3)

this model

Spaces using agbalu/Jugurtha-4B-GGUF 2

Collection including agbalu/Jugurtha-4B-GGUF

Jugurtha — Foundation & Reasoning Models

Collection

First and second-generation Kabyle reasoning LLMs (Jugurtha-4B and Jugurtha-2-9B) in BF16, GGUF, and MLX formats. • 7 items • Updated about 22 hours ago • 1