Decision Workspace
boostr vs torsh-quantization vs realizar
Side-by-side comparison of Rust crates
52
boostr
experimentalv0.1.0
ML framework built on numr - attention, quantization, model architectures
59
torsh-quantization
experimentalv0.1.1
Model quantization for ToRSh neural networks
60
realizar
experimentalv0.8.3
Pure Rust ML inference engine built from scratch - model serving for GGUF and safetensors
Core Metrics
| boostr | torsh-quantization | realizar | |
|---|---|---|---|
| Health Score | 52 | 59 | 60 |
| Total Downloads | 172 | 563 | 4.8K |
| 30d Downloads | 172 | 60 | 1.9K |
| Dependents | 17 | 7 | 114 |
| Releases | 2 | 6 | 34 |
| Last Updated | 13d ago | 7d ago | 11d ago |
| Age | 13d | 5m | 4m |
Health Breakdown
boostr
Maintenance
13
Quality
12
Community
9
Popularity
3
Documentation
15
torsh-quantization
Maintenance
20
Quality
13
Community
8
Popularity
3
Documentation
15
realizar
Maintenance
19
Quality
10
Community
12
Popularity
4
Documentation
15
Technical Details
| boostr | torsh-quantization | realizar | |
|---|---|---|---|
| Version | 0.1.0 | 0.1.1 | 0.8.3 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | Apache-2.0 | Apache-2.0 | MIT |
| Dependencies | 20 | 11 | 61 |
| Crate Size | 635KB | 277KB | 6.1MB |
| Features | 8 | 3 | 20 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2021 | 2021 |
| MSRV | 1.85 | 1.77 | 1.89 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •realizar leads with a health score of 60/100, but none of the options score above 80.
- •realizar is depended on by 114 crates — strongest ecosystem trust.