README.md

---
license: apache-2.0
library_name: mlx
pipeline_tag: feature-extraction
base_model: Qwen/Qwen3-Embedding-8B
tags:
- mlx
- embeddings
- feature-extraction
- sentence-similarity
- quantization
- omlx
---

# Qwen3-Embedding-8B — MLX BF16

> BF16 reference checkpoint for this matched local sweep.

This is the **BF16 MLX conversion** checkpoint from a matched local embedding-quantization experiment. It is published with explicit lineage, calibration evidence where applicable, and the bounded evaluation result that accompanied the conversion.

## Provenance and lineage

- Upstream model: [`Qwen/Qwen3-Embedding-8B`](https://huggingface.co/Qwen/Qwen3-Embedding-8B)
- Upstream revision recorded for publication: `1d8ad4ca9b3dd8059ad90a75d4983776a23d44af`
- Revision evidence: exact source snapshot retained in the local Hugging Face download metadata
- Direct parent: [`Qwen/Qwen3-Embedding-8B`](https://huggingface.co/Qwen/Qwen3-Embedding-8B)
- Conversion rule: every quantized checkpoint branches directly from the family MLX BF16 checkpoint; no lossy checkpoint was used to create another.
- Quantization: BF16 MLX conversion
- Local conversion stack: oMLX 0.5.3, mlx-lm 0.31.3, MLX 0.32.0
- Full collection: [MLX Embedding Quantization Matrix](https://huggingface.co/collections/TiGa-RCE/mlx-embedding-quantization-matrix-q-oq-oqe-at-4-6-8-bit-6a68d11afb238d4fe967d70b)

`PROVENANCE.json` contains machine-readable lineage and SHA-256 hashes for the published weight files. No importance matrix was used for this checkpoint.

## Bounded local evaluation

| Role | Retrieval smoke |
|---|---|
| BF16 reference | 24/24 top-1, MRR 1.0 |

The evaluation used 24 frozen query/document pairs, the upstream query instruction recipe, last-token pooling, L2 normalization, and direct comparison with vectors from the family BF16 checkpoint. This is an engineering smoke test, not MTEB and not a claim of universal quality. Retrieval success and representation fidelity are reported separately.

## Runtime scope

This checkpoint targets Apple Silicon through MLX/oMLX. CUDA and PyTorch results are a separate control lane and must not be interpreted as measurements of MLX/Metal kernel performance.

## License and attribution

Apache-2.0, following the upstream model card. The original model authors retain attribution for the upstream model; this repository contains a local MLX conversion or quantized derivative prepared by TiGa-RCE for reproducibility research.