arlenecc/jina-reranker-v3.5-mlx-q4

AI model by arlenecc

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

4-bit quantized version of jinaai/jina-reranker-v3.5-mlx, a domain-ready multilingual listwise reranker optimized for Apple Silicon. All Linear layers (attention + MLP) are quantized to 4-bit affine with groupsize=64. Embeddings and the projector stay in bf16 for accuracy. 0.56 GB vs 1.19 GB (53% smaller) with no measurable quality loss on MTEB reranking benchmarks. Measured against the bf16 original on MTEB reranking tasks (identical candidates across models): q4 matches bf16 within noise on all three datasets. See BENCHMARK.md for full methodology. The 8-bit variant is also available. The quantized weights use the standard MLX quantization format. Loaders that…

arlenecc/jina-reranker-v3.5-mlx-q4 on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-31T07:29:27.606Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

original paper

Documentation belongs to its respective authors. Reported project/model license: cc-by-nc-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

arlenecc/jina-reranker-v3.5-mlx-q4 is a task-unspecified model repository published by arlenecc on Hugging Face. The source reports the mlx library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: Not reported
Library: mlx
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: 596,049,920
Architecture: JinaForRanking
License: cc-by-nc-4.0
Access: Not gated by Hugging Face
Created: 2026-10-31T06:47:48.000Z
Last modified: 2026-10-31T06:48:44.000Z

Compatibility and lineage

Reported languages: multilingual

Reported base models: jinaai/jina-reranker-v3.5-mlx

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-10-31T06:50:12.924Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source