Sponsored by Vmake Labs Video Enhancer
Toolify Toolify logo
AI Models
granite-embedding-30m-sparse-coreml

FluidInference / granite-embedding-30m-sparse-coreml

Run on huggingface.co
huggingface.co
Total runs: 51
24-hour runs: 0
7-day runs: 19
30-day runs: 19
Model's Last Updated: October 09 2026
feature-extraction

Introduction of granite-embedding-30m-sparse-coreml

Model Details of granite-embedding-30m-sparse-coreml

Granite Embedding 30M Sparse for Core ML

Core ML conversion of IBM's ibm-granite/granite-embedding-30m-sparse (revision ad82b1fd ), the learned sparse encoder behind Intelligent Internet's Evoke . It turns text into a short list of weighted vocabulary terms, including related terms the text never uses ("vaccines for seniors" → vaccine, vaccination, older, elder, …), which go into an ordinary inverted index next to BM25. 30M parameters, fp16, Apache-2.0. IBM authored the model; Fluid Inference converted it.

Packages
Package Input Output Size
granite-embedding-30m-sparse-L64-fp16.mlpackage input_ids int32 [1, 64] max_logits fp16 [1, 192] , vocab_ids int32 [1, 192] 58 MB
granite-embedding-30m-sparse-L128-fp16.mlpackage [1, 128] same 58 MB
granite-embedding-30m-sparse-L256-fp16.mlpackage [1, 256] same 58 MB
granite-embedding-30m-sparse-L512-fp16.mlpackage [1, 512] same 58 MB

One package per sequence length (fixed shapes keep the graph on the Neural Engine; enumerated shapes ran entirely on CPU). macOS 14 / iOS 17 or newer.

  • Input: RoBERTa byte-level BPE ( tokenizer.json ), <s> … </s> , right-padded with <pad> (id 1) to the package length. The attention mask is derived from <pad> inside the graph.
  • Output: the 192 vocabulary terms with the highest MLM logit at any token position (max-pooled over tokens), sorted descending.
  • Weights (host side, fp32): w = log1p(max(v, 0)) ^ gamma × scale over the first active_dims , keep w > 0 . config.json holds Evoke P2.2's constants: queries keep 50 terms (gamma 1.8519, scale 0.6964), documents keep 192 (gamma 0.5628, scale 1.0). Score = Σ query weight × document weight over shared terms.
Accuracy

Against Evoke's shipped ONNX compilers ( Intelligent-Internet/Evoke-Model-Beta-1 ), NFCorpus test (323 queries, 3,633 documents), sparse dot over the semantic terms only:

Encoder nDCG@10 Recall@100 Recall@1000 Same top-10 as ONNX
ONNX (shipped, CPU) 0.3402 0.2956 0.5854 —
Core ML fp16, GPU 0.3405 0.2957 0.5856 99.6%
Core ML fp16, Neural Engine 0.3405 0.2953 0.5847 98.7%

An fp32 build (not uploaded) reproduces the ONNX term sets exactly (200/200 queries and documents); the fp16 differences are low-weight terms at the top-k boundary.

Speed

Apple M5 Pro, macOS 27, one warm call (median of 100), Swift:

Length Neural Engine GPU CPU
64 0.74–0.87 ms 2.5–3.3 ms 2.8–3.1 ms
128 1.2–1.4 ms 1.5–4.3 ms 4.1 ms
256 2.9 ms 1.9–3.4 ms 9.5–15 ms
512 7.6 ms 2.6 ms 16–27 ms

Use the Neural Engine up to 128 tokens and the GPU beyond. 160 of 172 ops run on the Neural Engine; token lookup, mask setup and the final top-k stay on CPU. After several seconds idle the first Neural Engine call takes ~15 ms. Encoding 3,633 NFCorpus documents: 14.1 s Core ML GPU vs 88.2 s ONNX Runtime CPU.

Use from Swift

FluidUse wraps the packages ( EvokeManager , Swift RoBERTa tokenizer with token ids identical to the Python tokenizer, host-side weighting; PR #28 ) and includes EvokeSearchDemo , an auto-playing search-as-you-type demo.

Runs of FluidInference granite-embedding-30m-sparse-coreml on huggingface.co

51
Total runs
0
24-hour runs
2
3-day runs
19
7-day runs
19
30-day runs

More Information About granite-embedding-30m-sparse-coreml huggingface.co Model

More granite-embedding-30m-sparse-coreml license Visit here:

https://choosealicense.com/licenses/apache-2.0

granite-embedding-30m-sparse-coreml huggingface.co

granite-embedding-30m-sparse-coreml huggingface.co is an AI model on huggingface.co that provides granite-embedding-30m-sparse-coreml's model effect (), which can be used instantly with this FluidInference granite-embedding-30m-sparse-coreml model. huggingface.co supports a free trial of the granite-embedding-30m-sparse-coreml model, and also provides paid use of the granite-embedding-30m-sparse-coreml. Support call granite-embedding-30m-sparse-coreml model through api, including Node.js, Python, http.

granite-embedding-30m-sparse-coreml huggingface.co Url

https://huggingface.co/FluidInference/granite-embedding-30m-sparse-coreml

FluidInference granite-embedding-30m-sparse-coreml online free

granite-embedding-30m-sparse-coreml huggingface.co is an online trial and call api platform, which integrates granite-embedding-30m-sparse-coreml's modeling effects, including api services, and provides a free online trial of granite-embedding-30m-sparse-coreml, you can try granite-embedding-30m-sparse-coreml online for free by clicking the link below.

FluidInference granite-embedding-30m-sparse-coreml online free url in huggingface.co:

https://huggingface.co/FluidInference/granite-embedding-30m-sparse-coreml

granite-embedding-30m-sparse-coreml install

granite-embedding-30m-sparse-coreml is an open source model from GitHub that offers a free installation service, and any user can find granite-embedding-30m-sparse-coreml on GitHub to install. At the same time, huggingface.co provides the effect of granite-embedding-30m-sparse-coreml install, users can directly use granite-embedding-30m-sparse-coreml installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

granite-embedding-30m-sparse-coreml install url in huggingface.co:

https://huggingface.co/FluidInference/granite-embedding-30m-sparse-coreml

Url of granite-embedding-30m-sparse-coreml

granite-embedding-30m-sparse-coreml huggingface.co Url

Provider of granite-embedding-30m-sparse-coreml huggingface.co

FluidInference
ORGANIZATIONS
huggingface.co

Other API from FluidInference