Decision Workspace
wasmicro vs ruvector-attention-wasm vs oxibonsai-model
Side-by-side comparison of Rust crates
52
wasmicro
experimentalv0.3.1
Tiny transformer inference for the web. BERT, GPT-2 and T5 in a 199 KB WASM bundle.
57
ruvector-attention-wasm
growingv2.3.0
High-performance WebAssembly attention mechanisms: Multi-Head, Flash, Hyperbolic, MoE, CGT Sheaf Attention with GPU acceleration for transformers and LLMs
57
oxibonsai-model
experimentalv0.2.3
Qwen3-8B Transformer implementation for OxiBonsai 1-bit inference
Core Metrics
| wasmicro | ruvector-attention-wasm | oxibonsai-model | |
|---|---|---|---|
| Health Score | 52 | 57 | 57 |
| Total Downloads | 128 | 124 | 1.1K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 40 |
| Releases | 7 | 6 | 10 |
| Last Updated | 123d ago | 13d ago | 80d ago |
| Age | 4m | 10m | 6m |
Health Breakdown
wasmicro
Maintenance
14
Quality
16
Community
6
Popularity
3
Documentation
13
ruvector-attention-wasm
Maintenance
18
Quality
17
Community
6
Popularity
3
Documentation
13
oxibonsai-model
Maintenance
15
Quality
13
Community
10
Popularity
4
Documentation
15
Technical Details
| wasmicro | ruvector-attention-wasm | oxibonsai-model | |
|---|---|---|---|
| Version | 0.3.1 | 2.3.0 | 0.2.3 |
| Stable (≥1.0) | ✗ No | ✓ Yes | ✗ No |
| License | MIT OR Apache-2.0 | MIT | Apache-2.0 |
| Dependencies | 6 | 9 | 14 |
| Crate Size | 75KB | 86KB | 465KB |
| Features | 5 | 1 | 3 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | — | — | 1.86 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •ruvector-attention-wasm leads with a health score of 57/100, but none of the options score above 80.
- •oxibonsai-model has the most downloads (1.1K), suggesting wider adoption.
- •wasmicro, oxibonsai-model are pre-1.0 — API may change.