✨ Quark v0.1 released

Next-gen intelligence, scaled down.

Building highly efficient, logic-driven Small Language Models that run natively on edge hardware and consumer devices.

Available Models

Bilingual

Quark-135M 135M

A lightweight bilingual language model optimized for speed and localized logic. Click to expand variants.

Features GQA, SwiGLU, RMSNorm, and RoPE. Trained on 50B+ tokens of ultra-curated data.

Featured Model

Quark-270M 270M

Our scaled small model featuring 32 layers and 768 hidden dimensions for advanced reasoning capabilities.

Equipped with a dense 65K vocabulary. Specially designed for multi-turn instruct fine-tuning.

Legacy

Quark-50M 50M

Our compact 50M parameter model — engineered for extremely hyper-low resource systems.

Lightweight and highly volatile, ideal for basic sequence prediction and embedded units.

Explore Weights →
Specialized

Quark-Math-Code 36M

Deep-thin experimental architecture engineered specifically for STEM tracking and math code parsing.

14 layers. Actively pre-training on a 5B token target with embedded Chain-of-Thought datasets.

Training Active
Safety Matrix

Quark-Mod Classifier

A high-throughput multi-label moderation engine covering 9 toxicity and cyber-safety categories.

Detects: toxic, severe_toxic, obscene, threat, insult, identity_hate, and advanced content exploits.

View Classifier →

Core Focus Areas

Hyper-Efficient

Mastering sub-1B parameters using Grouped-Query Attention (GQA) architectures.

🧠

Embedded CoT

Integrating step-by-step reasoning logic directly into the pre-training tokens.

🌍

Bilingual Focus

High-density blending of localized Italian, English, and technical STEM pipelines.

💻

True Open Source

All weights, configurations, and baseline streaming datasets are entirely open to the world.

Open Ecosystem Index

Repository Object Distribution Target
📚 Quark-135M Base Foundational localized small baseline language matrix.
🌐 Quark-135M Bilingual Bilingual (IT + EN) checkpoint trained on balanced multi-source pools.
🚀 Quark-270M Instruct Multi-turn conversation alignment model with strict formatting safety.
⚙️ Quark-270M Base Base engine ready for specialized downstream task tokenization.
📦 Quark-50M Legacy foundational checkpoint for exploratory sequence architectures.
🛡️ Quark-Mod Production safety guardrail classifier for modern pipeline filtering.
⚡️ Complete Collection (v0.1) Unified access hub to all current generation architectural releases.
💻 GitHub Organization Training codebases, data streaming pipelines, and infrastructure layers.