harshitkhandelwal208/hk
HK is a unified neural model format and framework built in native Zig, designed to replace SafeTensors, GGUF, and PyTorch checkpoints. Features zero-copy mmap loading, dual-mode quantization, 2:4 hardware sparsity, live model expansion, and 137+ architecture support with bindings for Python, Rust, Go, C#, Java, and TypeScript.
Growth
- Last 24 hours
- +0
- stars
- Last 7 days
- +0
- stars
- Last 30 days
- +20
- stars
- Total stars
- 23
- 3 a month ago
- Forks
- 2
- 0 contributors
Star history
Last 12 weeks · weekly cumulative stars · created Sep 13, 2026, zero before · computed from public GitHub star events
Rank in its topics
| Topic | Today | This week | This month |
|---|---|---|---|
| Zig | – | – | #23of 45 |
| LLM | – | – | #306of 431 |
README
hk
HK is a unified neural model format and framework built in native Zig, designed to replace SafeTensors, GGUF, and PyTorch checkpoints. Features zero-copy mmap loading, dual-mode quantization, 2:4 hardware sparsity, live model expansion, and 137+ architecture support with bindings for Python, Rust, Go, C#, Java, and TypeScript.
Upstar hasn’t fetched this README yet. Read it on GitHub.