Decision Workspace
ruvector-dither vs torsh-quantization vs cortiq-core
Side-by-side comparison of Rust crates
44
ruvector-dither
experimentalv0.1.0
Deterministic low-discrepancy dithering for low-bit quantization: golden-ratio and π-digit sequences for blue-noise error shaping
60
torsh-quantization
growingv0.2.0
Model quantization for ToRSh neural networks
60
cortiq-core
experimentalv0.8.14
CMF (Cortiq Model Format): a self-describing, memory-mappable binary container for quantized LLM weights, tokenizer, per-task masks and per-skill delta records.
Core Metrics
| ruvector-dither | torsh-quantization | cortiq-core | |
|---|---|---|---|
| Health Score | 44 | 60 | 60 |
| Total Downloads | 1.1K | 822 | 4.9K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 1 | 10 | 631 |
| Releases | 1 | 9 | 144 |
| Last Updated | 224d ago | 57d ago | 1d ago |
| Age | 7m | 1y | 3m |
Health Breakdown
ruvector-dither
Maintenance
4
Quality
16
Community
7
Popularity
4
Documentation
13
torsh-quantization
Maintenance
19
Quality
14
Community
9
Popularity
3
Documentation
15
cortiq-core
Maintenance
20
Quality
11
Community
13
Popularity
4
Documentation
12
Technical Details
| ruvector-dither | torsh-quantization | cortiq-core | |
|---|---|---|---|
| Version | 0.1.0 | 0.2.0 | 0.8.14 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT OR Apache-2.0 | Apache-2.0 | Apache-2.0 |
| Dependencies | 1 | 11 | 10 |
| Crate Size | 12KB | 288KB | 163KB |
| Features | 2 | 3 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | — | 1.87 | 1.88 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •torsh-quantization leads with a health score of 60/100, but none of the options score above 80.
- •cortiq-core has the most downloads (4.9K), suggesting wider adoption.
- •cortiq-core is depended on by 631 crates — strongest ecosystem trust.