Decision Workspace
oxibonsai-model vs ruvllm vs oxillama-arch
Side-by-side comparison of Rust crates
56
oxibonsai-model
experimentalv0.1.4
Qwen3-8B Transformer implementation for OxiBonsai 1-bit inference
59
ruvllm
experimentalv2.2.1
LLM serving runtime with Ruvector integration - Paged attention, KV cache, and SONA learning
55
oxillama-arch
experimentalv0.1.3
Model architecture implementations — LLaMA, Qwen3, Mistral, Gemma, Phi
Core Metrics
| oxibonsai-model | ruvllm | oxillama-arch | |
|---|---|---|---|
| Health Score | 56 | 59 | 55 |
| Total Downloads | 293 | 16.1K | 185 |
| 30d Downloads | 0 | 8.6K | 0 |
| Dependents | 20 | 3 | 16 |
| Releases | 5 | 10 | 4 |
| Last Updated | 9d ago | 20d ago | 20d ago |
| Age | 1m | 5m | 1m |
Health Breakdown
oxibonsai-model
Maintenance
15
Quality
13
Community
10
Popularity
3
Documentation
15
ruvllm
Maintenance
19
Quality
15
Community
8
Popularity
5
Documentation
12
oxillama-arch
Maintenance
15
Quality
16
Community
9
Popularity
3
Documentation
12
Technical Details
| oxibonsai-model | ruvllm | oxillama-arch | |
|---|---|---|---|
| Version | 0.1.4 | 2.2.1 | 0.1.3 |
| Stable (≥1.0) | ✗ No | ✓ Yes | ✗ No |
| License | Apache-2.0 | MIT | Apache-2.0 |
| Dependencies | 14 | 44 | 7 |
| Crate Size | 412KB | 1.2MB | 278KB |
| Features | 3 | 25 | 26 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | 1.86 | 1.77 | 1.89 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •ruvllm leads with a health score of 59/100, but none of the options score above 80.
- •oxibonsai-model, oxillama-arch are pre-1.0 — API may change.