Decision Workspace
llm-samplers vs ggml-sys-bleedingedge vs ghost-flow
Side-by-side comparison of Rust crates
42
llm-samplers
growingv0.0.7
Token samplers for large language models
51
ggml-sys-bleedingedge
growingv2404291813.0.0+llamacpp-release.b2757
Bleeding edge low-level bindings to GGML.
50
ghost-flow
experimentalv1.7.0
Complete machine learning framework in Rust - tensors, neural networks, 85+ ML algorithms, GPU acceleration, WASM, FFI, model serving, compiler optimizations, distributed training, and 8 hardware accelerators - all included by default
Core Metrics
| llm-samplers | ggml-sys-bleedingedge | ghost-flow | |
|---|---|---|---|
| Health Score | 42 | 51 | 50 |
| Total Downloads | 110.2K | 683.8K | 141 |
| 30d Downloads | 5.3K | 514 | 12 |
| Dependents | 48 | 6 | 0 |
| Releases | 6 | 493 | 8 |
| Last Updated | 869d ago | 697d ago | 67d ago |
| Age | 2y 9m | 2y 11m | 2m |
Health Breakdown
llm-samplers
Maintenance
4
Quality
14
Community
8
Popularity
6
Documentation
10
ggml-sys-bleedingedge
Maintenance
10
Quality
19
Community
5
Popularity
7
Documentation
10
ghost-flow
Maintenance
9
Quality
19
Community
6
Popularity
3
Documentation
13
Technical Details
| llm-samplers | ggml-sys-bleedingedge | ghost-flow | |
|---|---|---|---|
| Version | 0.0.7 | 2404291813.0.0+llamacpp-release.b2757 | 1.7.0 |
| Stable (≥1.0) | ✗ No | ✓ Yes | ✓ Yes |
| License | MIT | MIT | MIT OR Apache-2.0 |
| Dependencies | 4 | 3 | 10 |
| Crate Size | 28KB | 9.0MB | 23KB |
| Features | 0 | 10 | 12 |
| Yanked % | 0.0% | 0.4% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | — | — | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •ggml-sys-bleedingedge leads with a health score of 51/100, but none of the options score above 80.
- •⚠ llm-samplers, ggml-sys-bleedingedge have not been updated in over a year.
- •llm-samplers is pre-1.0 — API may change.