---
title: tencent/R3-embedding-0.6b
description: "The latest agent skill retrieval model at the 0.6B scale. R3-Embedding is the bi-encoder (recall) stage of R3-Skill's two-stage retriever fo. Qwen3, 596M parameters."
canonical_url: https://superlinked.com/models/tencent-r3-embedding-0-6b
last_updated: 2026-08-24
---

# tencent/R3-embedding-0.6b

The latest agent skill retrieval model at the 0.6B scale. R3-Embedding is the bi-encoder (recall) stage of R3-Skill's two-stage retriever for query-conditional agent skill retrieval.

Source: [tencent/R3-embedding-0.6b on HuggingFace](https://huggingface.co/tencent/R3-embedding-0.6b)
Base model: [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Qwen3 |
| Parameters | 596M |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 1,024 |
| Max sequence length | 4,096 tokens |
| License | apache-2.0 |
| Inputs | text |

## Benchmarks

### R3Skill

Domain: technology · Task: retrieval · Language: en

Agent skill retrieval: match user requests to the SKILL.md that solves them (Tencent R3 release set)

Corpus: 2,050 · Queries: 5,696

**Quality:** ndcg at 10: 0.8158

**Performance (L4 b1 c16):** Corpus 24.5K tok/s · Corpus p50 197.0ms · Query 22.4K tok/s · Query p50 113.7ms

[Reference](https://huggingface.co/tencent/R3-embedding-0.6b)