Decision Workspace
brainwires-finetune vs rullama-finetune vs qlora-rs
Side-by-side comparison of Rust crates
47
brainwires-finetune
experimentalv0.11.0
Cloud fine-tune APIs (OpenAI, Anthropic, Together, Fireworks, Anyscale, Bedrock, Vertex AI) + dataset pipelines for the Brainwires Agent Framework. Local LoRA/QLoRA/DoRA fine-tuning and training-from-scratch live in the sibling `rullama` workspace (`rullama-finetune`, `rullama-training`).
53
rullama-finetune
experimentalv0.12.0
Cloud fine-tune APIs (OpenAI, Anthropic, Together, Fireworks, Anyscale, Bedrock, Vertex AI) for the rullama agent framework. Dataset pipelines live in `rullama-datasets`; local LoRA/QLoRA/DoRA fine-tuning lives in `rullama-lora`.
58
qlora-rs
growingv1.0.5
4-bit quantized LoRA (QLoRA) implementation with dual GGUF and Candle native export for Rust
Core Metrics
| brainwires-finetune | rullama-finetune | qlora-rs | |
|---|---|---|---|
| Health Score | 47 | 53 | 58 |
| Total Downloads | 35 | 151 | 767 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 1 | 1 | 12 |
| Releases | 1 | 6 | 5 |
| Last Updated | 54d ago | 12d ago | 166d ago |
| Age | 1m | 2m | 6m |
Health Breakdown
brainwires-finetune
Maintenance
10
Quality
14
Community
6
Popularity
2
Documentation
15
rullama-finetune
Maintenance
15
Quality
14
Community
6
Popularity
3
Documentation
15
qlora-rs
Maintenance
14
Quality
17
Community
9
Popularity
3
Documentation
15
Technical Details
| brainwires-finetune | rullama-finetune | qlora-rs | |
|---|---|---|---|
| Version | 0.11.0 | 0.12.0 | 1.0.5 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | MIT OR Apache-2.0 | MIT OR Apache-2.0 | MIT |
| Dependencies | 24 | 21 | 18 |
| Crate Size | 68KB | 43KB | 81KB |
| Features | 9 | 5 | 5 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2024 | 2021 |
| MSRV | 1.91 | 1.91 | 1.92 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •qlora-rs leads with a health score of 58/100, but none of the options score above 80.
- •brainwires-finetune, rullama-finetune are pre-1.0 — API may change.