Decision Workspace
ruvllm vs oxibonsai-model vs mistralrs-kv-cache
Side-by-side comparison of Rust crates
59
ruvllm
experimentalv2.2.1
LLM serving runtime with Ruvector integration - Paged attention, KV cache, and SONA learning
56
oxibonsai-model
experimentalv0.1.4
Qwen3-8B Transformer implementation for OxiBonsai 1-bit inference
52
mistralrs-kv-cache
experimentalv0.3.0
Trait interface for compressed KV-cache implementations in mistral.rs
Core Metrics
| ruvllm | oxibonsai-model | mistralrs-kv-cache | |
|---|---|---|---|
| Health Score | 59 | 56 | 52 |
| Total Downloads | 16.1K | 293 | 230 |
| 30d Downloads | 8.6K | 0 | 0 |
| Dependents | 3 | 20 | 4 |
| Releases | 10 | 5 | 3 |
| Last Updated | 20d ago | 9d ago | 36d ago |
| Age | 5m | 1m | 1m |
Health Breakdown
ruvllm
Maintenance
19
Quality
15
Community
8
Popularity
5
Documentation
12
oxibonsai-model
Maintenance
15
Quality
13
Community
10
Popularity
3
Documentation
15
mistralrs-kv-cache
Maintenance
12
Quality
14
Community
8
Popularity
3
Documentation
15
Technical Details
| ruvllm | oxibonsai-model | mistralrs-kv-cache | |
|---|---|---|---|
| Version | 2.2.1 | 0.1.4 | 0.3.0 |
| Stable (≥1.0) | ✓ Yes | ✗ No | ✗ No |
| License | MIT | Apache-2.0 | MIT OR Apache-2.0 |
| Dependencies | 44 | 14 | 1 |
| Crate Size | 1.2MB | 412KB | 17KB |
| Features | 25 | 3 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | 1.77 | 1.86 | 1.75 |
| 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, mistralrs-kv-cache are pre-1.0 — API may change.