# Qwen3-Embedding-4B vs Qwen3-Embedding-8B (slim)

> Qwen3-Embedding-8B scores 74.7 (BB) to Qwen3-Embedding-4B's 72.9 (BB) for text embeddings. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/qwen3-embedding-4b-vs-qwen3-embedding-8b.md (~2,150 tokens) · this version ~380 tokens · JSON https://www.anchorterminal.com/compare/qwen3-embedding-4b-vs-qwen3-embedding-8b.json · canonical https://www.anchorterminal.com/compare/qwen3-embedding-4b-vs-qwen3-embedding-8b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-21
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Qwen3-Embedding-8B scores 74.7 (BB) on agent readiness against Qwen3-Embedding-4B's 72.9 (BB), and leads in 1 of 5 scored categories. Both do text embeddings.

- Qwen3-Embedding-4B: BB 72.9, rank #3 of 100 open-weight models · https://www.anchorterminal.com/tools/qwen3-embedding-4b.min.md
- Qwen3-Embedding-8B: BB 74.7, rank #1 of 100 open-weight models · https://www.anchorterminal.com/tools/qwen3-embedding-8b.min.md
- Qwen3-Embedding-4B, good for Agents that need local multilingual text or code retrieval on a laptop, a small GPU or a CPU, with a plain licence.
- Qwen3-Embedding-8B, good for Agents that need local multilingual text or code retrieval on a modest GPU or CPU, with the widest runtime support and a plain licence. Ahead on Capability, 86 against 81.

| Category | Qwen3-Embedding-4B | Qwen3-Embedding-8B |
| --- | --- | --- |
| Capability (35%) | 81 | 86 |
| Reach (25%) | 100 | 100 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 65 | 65 |
| Documentation and upkeep (10%) | 21 | 21 |

| Fact (where they differ) | Qwen3-Embedding-4B | Qwen3-Embedding-8B |
| --- | --- | --- |
| Last release | 2025-08-03 | 2025-07-15 |