EmbeddingsAvailable now

Qwen3 Embedding 0.6B

Your knowledge. Every language. One search.

Search across 100+ languages and code in one instruction-aware embedder, with 32K context and dimensions you can tune.

Start Building Compare with the flagships Hugging Face model card

Good for

01Search documents and code across more than 100 languages.
02Build multilingual RAG and enterprise knowledge systems.
03Retrieve relevant information from long documents efficiently.

Information systems & search
Coding
Helpdesk & support

Key facts

Model origin: Qwen
Context window: 32K tokens
Size: 0.6B
Modalities: text / code → vector
Languages: 100+
Dimensions: ≤ 1024
API model id: Model id published at launch
Availability: Available now. Regional rollout is shown in your Console. Ask us about your region.

Your data boundary

Prompts and outputs are not stored by default. Knowledge or Memory data that your organization intentionally persists is encrypted, pinned to the selected region, isolated to authorized organizational scopes, and never used to train shared or third-party models.

Works well with

ChatAvailable nowQwen 3.8Enterprise chat, coding & 1M context ReasoningComing soonDeepSeek 4.1 FlashPremium reasoning for complex challenges DecisionsAvailable nowClefIntelligent, confidence-scored decisions

More models

Qwen 3.8 Gemma 4 Clef FLUX.2 [klein]Whisper large v3 mxbai-embed-large v1 Kokoro DeepSeek 4.1 Flash GLM 5.3

Explore the platform

Start with control

Create your account and pick the region your data must stay in.

Create account Talk to us