Decision Workspace
rvllm vs llama-cpp-4 vs memra-sampling
Side-by-side comparison of Rust crates
43
rvllm
experimentalv0.1.0
Small LLM inference engine in Rust: paged KV cache, continuous batching, CPU and CUDA backends, GGUF loading
59
llama-cpp-4
growingv0.7.0
llama.cpp bindings for Rust
57
memra-sampling
experimentalv0.138.0
Host-side sampler chain (temperature/top-k/top-p/penalties, llama.cpp CPU sampler semantics) for the memra inference engine
Core Metrics
| rvllm | llama-cpp-4 | memra-sampling | |
|---|---|---|---|
| Health Score | 43 | 59 | 57 |
| Total Downloads | 9 | 30.4K | 2.1K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 24 | 86 |
| Releases | 1 | 77 | 87 |
| Last Updated | 3d ago | 30d ago | 28d ago |
| Age | 3d | 1y 11m | 2m |
Health Breakdown
rvllm
Maintenance
13
Quality
13
Community
6
Popularity
1
Documentation
10
llama-cpp-4
Maintenance
17
Quality
17
Community
10
Popularity
5
Documentation
10
memra-sampling
Maintenance
17
Quality
15
Community
11
Popularity
4
Documentation
10
Technical Details
| rvllm | llama-cpp-4 | memra-sampling | |
|---|---|---|---|
| Version | 0.1.0 | 0.7.0 | 0.138.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | MIT OR Apache-2.0 | FSL-1.1-ALv2 |
| Dependencies | 17 | 6 | 0 |
| Crate Size | 109KB | 224KB | 20KB |
| Features | 5 | 16 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2021 | 2021 |
| MSRV | — | — | 1.97 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •llama-cpp-4 leads with a health score of 59/100, but none of the options score above 80.