---
title: Qwen/Qwen3-0.6B
description: Qwen/Qwen3-0.6B — Qwen3 model with 600M parameters.
canonical_url: https://superlinked.com/models/qwen-qwen3-0-6b
last_updated: 2026-06-29
---

# Qwen/Qwen3-0.6B

Source: [Qwen/Qwen3-0.6B on HuggingFace](https://huggingface.co/Qwen/Qwen3-0.6B)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Qwen3 |
| Parameters | 600M |
| Tasks | Generate |
| Outputs | Text |
| Context window | 4,096 tokens |
| Max output | 1,024 tokens |
| Capabilities | streaming |
| License | apache-2.0 |
| Inputs | text |

## Benchmarks

### CaseHOLD

Domain: legal · Task: generation · Language: en

**Quality:** accuracy: 0.4600

**Performance (RTX-PRO-6000 b1 c4):** Corpus 621 tok/s · Corpus p50 1.7s

### GPQA Diamond

Domain: scientific · Task: generation · Language: en

**Quality:** accuracy: 0.2475

**Performance (RTX-PRO-6000 b1 c4):** Corpus 598 tok/s · Corpus p50 508.2ms

### MedQA

Domain: medical · Task: generation · Language: en

**Quality:** accuracy: 0.2533

**Performance (RTX-PRO-6000 b1 c4):** Corpus 593 tok/s · Corpus p50 317.4ms

### MMLU-Pro

Domain: general · Task: generation · Language: en

**Quality:** accuracy: 0.2367

**Performance (RTX-PRO-6000 b1 c4):** Corpus 573 tok/s · Corpus p50 216.5ms