---
license: apache-2.0
library_name: mlx
pipeline_tag: feature-extraction
base_model: TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-BF16
tags:
- mlx
- embeddings
- feature-extraction
- sentence-similarity
- quantization
- omlx
- q6
- 6-bit
---

# gte-Qwen2-1.5B-instruct — MLX Q6

> This checkpoint passed the bounded local representation-fidelity gate described below.

This is the **Q uniform affine quantization** 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: [`Alibaba-NLP/gte-Qwen2-1.5B-instruct`](https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct)
- Upstream revision recorded for publication: `a9af15a6372d7d6b25e9fb07c2ccb9e1fe645644`
- Revision evidence: upstream revision verified at publication time; historical local snapshot metadata was not retained
- Direct parent: [`TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-BF16`](https://huggingface.co/TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-BF16)
- Conversion rule: every quantized checkpoint branches directly from the family MLX BF16 checkpoint; no lossy checkpoint was used to create another.
- Quantization: Q uniform affine quantization, nominal 6-bit, group size 64
- 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

| Metric | Result |
|---|---:|
| Top-1 retrieval | 1.000 |
| MRR | 1.000 |
| Mean aligned cosine vs BF16 | 0.997786 |
| Minimum aligned cosine vs BF16 | 0.996132 |
| Score RMSE vs BF16 | 0.004667 |
| Queries with rank change | 0 |
| Predeclared gate | PASS |

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.