AarambhDevHub/aarambh-studio
🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE, native video/document understanding, long-horizon tool agents, quantization-aware training. Scales: Tiny (25M) to Large (1.3B).
110
Stars
36
Forks
43.2
Radar Score
Rising
Momentum
Scoring Breakdown
Impact32.3
Velocity47.3
Health54.8
Growth Metrics
7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Rust
Why it ranks
Steady growth — consistently collecting stars and contributors.
LLM Frameworks · fine-tuningTop 54% globally