Instructions to use pyxon-ai/pyxon-sllm-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use pyxon-ai/pyxon-sllm-v0 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 pyxon-ai/pyxon-sllm-v0
# Run inference directly in the terminal:
llama cli -hf pyxon-ai/pyxon-sllm-v0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pyxon-ai/pyxon-sllm-v0
# Run inference directly in the terminal:
llama cli -hf pyxon-ai/pyxon-sllm-v0

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 pyxon-ai/pyxon-sllm-v0
# Run inference directly in the terminal:
./llama-cli -hf pyxon-ai/pyxon-sllm-v0

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 pyxon-ai/pyxon-sllm-v0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pyxon-ai/pyxon-sllm-v0

Use Docker

docker model run hf.co/pyxon-ai/pyxon-sllm-v0

LM Studio
Jan
Ollama
How to use pyxon-ai/pyxon-sllm-v0 with Ollama:
```
ollama run hf.co/pyxon-ai/pyxon-sllm-v0
```

Unsloth Studio

How to use pyxon-ai/pyxon-sllm-v0 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 pyxon-ai/pyxon-sllm-v0 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 pyxon-ai/pyxon-sllm-v0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pyxon-ai/pyxon-sllm-v0 to start chatting

How to use pyxon-ai/pyxon-sllm-v0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pyxon-ai/pyxon-sllm-v0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "pyxon-ai/pyxon-sllm-v0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use pyxon-ai/pyxon-sllm-v0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pyxon-ai/pyxon-sllm-v0

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 "pyxon-ai/pyxon-sllm-v0" \
  --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"

Docker Model Runner
How to use pyxon-ai/pyxon-sllm-v0 with Docker Model Runner:
```
docker model run hf.co/pyxon-ai/pyxon-sllm-v0
```

Lemonade

How to use pyxon-ai/pyxon-sllm-v0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pyxon-ai/pyxon-sllm-v0

Run and chat with the model

lemonade run user.pyxon-sllm-v0-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use pyxon-ai/pyxon-sllm-v0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pyxon-ai/pyxon-sllm-v0

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 pyxon-ai/pyxon-sllm-v0

Run Hermes

hermes

Atomic Chat

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Pyxon SLLM v0

Arabic-first small language model for edge and on-device AI
Built by PYXON.AI · Research · Labs · Production AI · Beta · v.2026

Why pay for a 7B cloud model when a 1.5B model on your device can carry the workload — especially with retrieval?
Try PYXON.AI →

What this is

Pyxon SLLM v0 is a ~1.5B Arabic instruction model fine-tuned for chat and edge deployment. It is part of PYXON AI Labs’ on-device research line: lightweight models that run offline, keep data on-device, and pair with retrieval (RAG) when accuracy must match larger cloud systems.


Name	`pyxon-sllm-v0`
Base	Qwen2.5-1.5B-Instruct
Focus	Modern Standard Arabic instruction-following
Method	QLoRA supervised fine-tuning on public Arabic datasets
Runtime artifact	`pyxon-sllm-v0.gguf` (q8_0)
Designed for	Phone / edge / Ollama / offline assistants

From the Labs

PYXON.AI is PYXON’s research division — scientists and engineers building AI that performs on Arabic-language and on-device challenges, not slides.

This release sits next to Pyxon On-Device RAG: research showing that small models plus device-specific retrieval can match or beat much larger baselines while staying compatible with mobile compute, memory, and privacy constraints.

Related research

Enhancing weak LLM performance on edge devices through retrieval-augmented generation — a benchmark study (Beta · 2026-03-28)

Hamza Salem, Ahmad Algraeeb, Almuhanad Al-Nihmy & Manuel Mazzara

RAG · edge computing · mobile · LLM · on-device AI · benchmarks

A 1,500-question benchmark from three phone manuals shows RAG lifting small on-device models to 100% accuracy versus ~21–37% without retrieval, with analysis of size, latency, and device-specific knowledge bases.

Hamza Salem — Head of Pyxon AI Department, PYXON.AI (hamzas@pyxon.ai)
Ahmad Algraeeb — PYXON AI Department (ahamdg@pyxon.ai)
Almuhanad Al-Nihmy — Kütahya Dumlupınar University
Manuel Mazzara — Innopolis University

More products and labs updates: www.pyxon.ai

Quick start (Ollama)

Place pyxon-sllm-v0.gguf next to Modelfile, then:

cd pyxon-sllm

# rename if you still have the old export name
# mv arabic-1.5b-q8_0.gguf pyxon-sllm-v0.gguf
# mv outputs/gguf/pyxon-sllm-v0.gguf ./pyxon-sllm-v0.gguf

ollama create pyxon-sllm-v0 -f Modelfile
ollama run pyxon-sllm-v0 "اشرح لي الذكاء الاصطناعي باختصار"

Publish

ollama signin
ollama create YOUR_USERNAME/pyxon-sllm-v0 -f Modelfile
ollama push YOUR_USERNAME/pyxon-sllm-v0

Others pull with:

ollama run YOUR_USERNAME/pyxon-sllm-v0

Training data (public)

Dataset	Role
`arbml/CIDAR`	Culturally reviewed Arabic instructions
`FreedomIntelligence/alpaca-gpt4-arabic`	Broad Arabic SFT
`CohereForAI/aya_dataset` (Arabic)	Multilingual quality filter
`FreedomIntelligence/evol-instruct-arabic`	Harder instructions (optional)

Reproduce the fine-tune

cd pyxon-sllm
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt

python prepare_data.py --include_evol
python train.py --data data/train.jsonl --eval_data data/val.jsonl
python merge_and_export.py --quant q8_0
# if merge already done:
# python merge_and_export.py --skip_merge --quant q8_0

Requires a GPU with ~16 GB VRAM for QLoRA. Checklist: llm.txt.

Intended use

Arabic chat / Q&A on edge devices
Offline or privacy-sensitive assistants
Backbone for on-device RAG (retrieve from local docs, then generate)

Not a substitute for specialist medical, legal, or safety-critical systems without human review.

Call to action

Research that actually works — Arabic-first, on-device, shipped.

→ www.pyxon.ai
→ Join Labs / careers: info@pyxon.com · hr@pyxon.com

Downloads last month: 9

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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