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 →Building highly efficient, logic-driven Small Language Models that run natively on edge hardware and consumer devices.
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.
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.
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 →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 ActiveA 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 →Mastering sub-1B parameters using Grouped-Query Attention (GQA) architectures.
Integrating step-by-step reasoning logic directly into the pre-training tokens.
High-density blending of localized Italian, English, and technical STEM pipelines.
All weights, configurations, and baseline streaming datasets are entirely open to the world.
| 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. |