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).
Why this job: topics: gguf, quantization
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 112
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v4.0.0
- Released 2 months ago
- Built with
- Rust
- 93% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 61 merged
- 0 waiting
- Releases
- 4
- 4 in the last year
More: languages, topics and project record
Languages
- Rust 93%
- Shell 5%
- Python 1%
- Cuda 1%
Topics
- ai-agents
- candle
- decoder-only
- deep-learning
- dora
- from-scratch
- gguf
- grpo
- large-language-model
- llm
- lora
- machine-learning
Project record
- JobLocal LLMs
- StatusListed
- Commits85
- Forks36
- Watching2
- Stars in 28 days+2
- CreatedJun 24, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026