Decision Workspace
bitnet-quantize vs ternlang-compress vs oxibonsai-core
Side-by-side comparison of Rust crates
55
bitnet-quantize
experimentalv0.2.1
Microsoft BitNet b1.58 quantization and inference for Rust
49
ternlang-compress
experimentalv1.3.6
LLM-to-ternary compression pipeline — quantize float models to {-1,0,+1}, build sparse zero-index, export .tern files for ternlang-ml inference.
59
oxibonsai-core
experimentalv0.1.4
GGUF Q1_0_g128 loader, tensor types, and configuration for OxiBonsai
Core Metrics
| bitnet-quantize | ternlang-compress | oxibonsai-core | |
|---|---|---|---|
| Health Score | 55 | 49 | 59 |
| Total Downloads | 874 | 115 | 361 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 12 | 0 | 45 |
| Releases | 3 | 9 | 5 |
| Last Updated | 117d ago | 19d ago | 9d ago |
| Age | 4m | 1m | 1m |
Health Breakdown
bitnet-quantize
Maintenance
13
Quality
14
Community
9
Popularity
4
Documentation
15
ternlang-compress
Maintenance
15
Quality
18
Community
6
Popularity
2
Documentation
8
oxibonsai-core
Maintenance
15
Quality
15
Community
11
Popularity
3
Documentation
15
Technical Details
| bitnet-quantize | ternlang-compress | oxibonsai-core | |
|---|---|---|---|
| Version | 0.2.1 | 1.3.6 | 0.1.4 |
| Stable (≥1.0) | ✗ No | ✓ Yes | ✗ No |
| License | MIT | LicenseRef-BSL-1.1 | Apache-2.0 |
| Dependencies | 12 | 13 | 7 |
| Crate Size | 58KB | 18KB | 82KB |
| Features | 4 | 6 | 3 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2024 | 2021 |
| MSRV | 1.92 | — | 1.86 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •oxibonsai-core leads with a health score of 59/100, but none of the options score above 80.
- •bitnet-quantize has the most downloads (874), suggesting wider adoption.
- •bitnet-quantize, oxibonsai-core are pre-1.0 — API may change.