Decision Workspace
llmnop vs inference-lab vs miyabi-llm
Side-by-side comparison of Rust crates
50
llmnop
experimentalv0.9.0
A command-line tool for benchmarking the performance of LLM inference endpoints.
51
inference-lab
experimentalv0.6.2
High-performance LLM inference simulator for analyzing serving systems
50
miyabi-llm
experimentalv1.1.0
LLM abstraction layer for Miyabi - GPT-OSS-20B integration
Core Metrics
| llmnop | inference-lab | miyabi-llm | |
|---|---|---|---|
| Health Score | 50 | 51 | 50 |
| Total Downloads | 1.1K | 246 | 1.9K |
| 30d Downloads | 15 | 45 | 283 |
| Dependents | 0 | 0 | 12 |
| Releases | 11 | 13 | 4 |
| Last Updated | 35d ago | 2d ago | 125d ago |
| Age | 8m | 3m | 5m |
Health Breakdown
llmnop
Maintenance
17
Quality
11
Community
6
Popularity
4
Documentation
12
inference-lab
Maintenance
19
Quality
13
Community
6
Popularity
3
Documentation
10
miyabi-llm
Maintenance
13
Quality
14
Community
9
Popularity
4
Documentation
10
Technical Details
| llmnop | inference-lab | miyabi-llm | |
|---|---|---|---|
| Version | 0.9.0 | 0.6.2 | 1.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | Apache-2.0 | MIT | Apache-2.0 |
| Dependencies | 15 | 24 | 19 |
| Crate Size | 2.0MB | 84KB | 54KB |
| Features | 1 | 3 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2021 | 2021 |
| MSRV | 1.85 | — | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •inference-lab leads with a health score of 51/100, but none of the options score above 80.
- •miyabi-llm has the most downloads (1.9K), suggesting wider adoption.
- •llmnop, inference-lab are pre-1.0 — API may change.