Decision Workspace
needle-core vs oxillama-quant vs classeve-rai-infer
Side-by-side comparison of Rust crates
56
needle-core
experimentalv0.3.1
no_std compute kernels for Needle: Cactus-Quants matmul, fast Walsh-Hadamard transform, attention, RoPE
54
oxillama-quant
experimentalv0.1.4
Quantization kernels for all GGUF quantization types
49
classeve-rai-infer
experimentalv0.2.5
CPU inference engine for 4-bit quantized LLMs — hand-written AVX2 GEMM kernels, .raimodel format, speculative decoding
Core Metrics
| needle-core | oxillama-quant | classeve-rai-infer | |
|---|---|---|---|
| Health Score | 56 | 54 | 49 |
| Total Downloads | 532 | 777 | 81 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 14 | 34 | 0 |
| Releases | 5 | 5 | 4 |
| Last Updated | 20d ago | 53d ago | 31d ago |
| Age | 4m | 5m | 4m |
Health Breakdown
needle-core
Maintenance
17
Quality
15
Community
9
Popularity
3
Documentation
12
oxillama-quant
Maintenance
15
Quality
14
Community
10
Popularity
3
Documentation
12
classeve-rai-infer
Maintenance
17
Quality
12
Community
6
Popularity
2
Documentation
12
Technical Details
| needle-core | oxillama-quant | classeve-rai-infer | |
|---|---|---|---|
| Version | 0.3.1 | 0.1.4 | 0.2.5 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | Apache-2.0 | Apache-2.0 |
| Dependencies | 4 | 7 | 12 |
| Crate Size | 126KB | 538KB | 522KB |
| Features | 5 | 5 | 2 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | 1.87 | 1.89 | 1.87 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •needle-core leads with a health score of 56/100, but none of the options score above 80.
- •oxillama-quant has the most downloads (777), suggesting wider adoption.