Comparison
Where candding sits next to fastembed, fastembed-rs, EmbedAnything, text-embeddings-inference, candle-transformers and hosted embedding APIs.
The table sets candding beside other ways to produce embeddings. A dash means this page has no verified fact for that cell, not that the project has nothing there.
| Project | Runtime | Language | Backends | How models are validated | Model surface | Serving |
|---|---|---|---|---|---|---|
| candding | candle, in-process | Rust | CPU and Apple Metal, verified per model; CUDA, verified per model on a T4 | every model against its own reference over the whole output, dense at cosine ≥ 0.9999 and max-abs ≤ 1e-4 in F32 on CPU, plus CPU-to-accelerator parity at cosine 0.999 | 35 dense models in nine families, 6 sparse, 4 multi-vector and 8 rerankers; the catalog lists them | none, you embed in your own process |
| fastembed (Python) | onnxruntime | Python | CPU and CUDA execution providers | canonical-vector tests on the first five dimensions at 1e-3 | dense, sparse, late interaction, rerankers, images | none, in-process library |
| fastembed-rs | onnxruntime through the ort crate | Rust | onnxruntime execution providers | — | — | none, in-process library |
| EmbedAnything | candle through candle-transformers, onnxruntime behind an optional feature | Rust, with Python bindings | CPU, CUDA, Metal through cargo features | — | dense, SPLADE, ColBERT, ColPali, CLIP, Whisper audio, rerankers | none, an in-process library that also ingests files, chunks them and writes to vector databases |
| text-embeddings-inference | candle | Rust, reached over HTTP | CPU, Metal, CUDA | snapshot tests at cosine 0.999 | — | a server, as a Docker image or a binary |
| candle-transformers examples | candle | Rust | CPU, Metal, CUDA through candle's features | — | a handful of embedding models | none, example programs rather than a library API |
| hosted embedding APIs | the provider's | any HTTP client | the provider's hardware | — | the provider's catalog | the provider's endpoint, priced per token |
candding stops at the vector or the score: it has no server, no Python bindings, and no chunking, parsing or storage. The roadmap plans the bindings, the pipelines around the catalog and the next model families, and testing has every assertion behind candding's validation cell.
Rerank output
What a reranker returns for a query and its documents, what each checkpoint's score means, how long inputs are cut, and each checkpoint's status.
Model catalog
Every model candding ships, generated from the registry: the dense, sparse, multi-vector and rerank catalogs, each row with its own per-device status.