Decision Workspace
kv-cache-size vs oxibonsai-model vs pictor-model
Side-by-side comparison of Rust crates
47
kv-cache-size
experimentalv0.1.1
Exact KV-cache arithmetic for transformer inference: bytes per token, total cache bytes, and the context length that fits a memory budget.
57
oxibonsai-model
experimentalv0.2.3
Qwen3-8B Transformer implementation for OxiBonsai 1-bit inference
46
pictor-model
experimentalv0.1.0
Qwen3-8B Transformer implementation for Pictor 1-bit inference
Core Metrics
| kv-cache-size | oxibonsai-model | pictor-model | |
|---|---|---|---|
| Health Score | 47 | 57 | 46 |
| Total Downloads | 28 | 1.1K | 172 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 40 | 2 |
| Releases | 2 | 10 | 1 |
| Last Updated | 31d ago | 80d ago | 96d ago |
| Age | 1m | 6m | 3m |
Health Breakdown
kv-cache-size
Maintenance
12
Quality
12
Community
6
Popularity
2
Documentation
15
oxibonsai-model
Maintenance
15
Quality
13
Community
10
Popularity
4
Documentation
15
pictor-model
Maintenance
8
Quality
13
Community
7
Popularity
3
Documentation
15
Technical Details
| kv-cache-size | oxibonsai-model | pictor-model | |
|---|---|---|---|
| Version | 0.1.1 | 0.2.3 | 0.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT OR Apache-2.0 | Apache-2.0 | Apache-2.0 |
| Dependencies | 0 | 14 | 14 |
| Crate Size | 3.3MB | 465KB | 431KB |
| Features | 0 | 3 | 3 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | 1.63 | 1.86 | 1.86 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •oxibonsai-model leads with a health score of 57/100, but none of the options score above 80.