๐ฆ Decoder-only LLM built from scratch in pure Rust using Candle โ 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).
Last updated Aug 9, 2026
74
Stars
20
Forks
1
Issues
+11
Stars/day
Attention Score
67
Topics
Language breakdown
No language data available.
โธ Files
click to expand
README
No README available.
