Decision Workspace
oomllama vs tibet-oomllama vs memvid-ask-model
Side-by-side comparison of Rust crates
39
oomllama
experimentalv1.0.0-alpha.2
Sovereign AI Inference Engine — .oom quantization, Trust Kernel encryption, JIS identity routing, TIBET provenance. The auto where trust-kernel is the motor.
42
tibet-oomllama
experimentalv0.1.0
OomLlama — Sovereign LLM runtime with .oom format, Q2/Q4/Q8 quantization, and lazy-loading inference
63
memvid-ask-model
growingv2.0.139
LLM inference module for Memvid Q&A with local and cloud model support
Core Metrics
| oomllama | tibet-oomllama | memvid-ask-model | |
|---|---|---|---|
| Health Score | 39 | 42 | 63 |
| Total Downloads | 24 | 22 | 877 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 25 |
| Releases | 2 | 1 | 27 |
| Last Updated | 36d ago | 70d ago | 73d ago |
| Age | 1m | 2m | 6m |
Health Breakdown
oomllama
Maintenance
12
Quality
12
Community
3
Popularity
2
Documentation
10
tibet-oomllama
Maintenance
9
Quality
15
Community
6
Popularity
2
Documentation
10
memvid-ask-model
Maintenance
16
Quality
18
Community
10
Popularity
4
Documentation
15
Technical Details
| oomllama | tibet-oomllama | memvid-ask-model | |
|---|---|---|---|
| Version | 1.0.0-alpha.2 | 0.1.0 | 2.0.139 |
| Stable (≥1.0) | ✓ Yes | ✗ No | ✓ Yes |
| License | MIT | MIT | Apache-2.0 |
| Dependencies | 41 | 15 | 9 |
| Crate Size | 2.2MB | 83KB | 53KB |
| Features | 3 | 5 | 2 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | — | — | 1.85.0 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •memvid-ask-model leads with a health score of 63/100, but none of the options score above 80.
- •tibet-oomllama is pre-1.0 — API may change.