Qwen3-Embedding-8B
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reason...
Params
7.6 B
Context
40,960
Downloads 30d
2.6 M
Likes
804
Download history
daily snapshots · 55 days
▲ 326 K in the last 30 days (11.2%)
2.9 M2.2 M
Aug 22Sep 1Sep 11Sep 20
3.4 M2.2 M
Jul 28Aug 15Sep 2Sep 20
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 15.1 GB | 18.3 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 40K ctx | 15.1 GB | 22.8 GB | ⚠️ Tight — reduce context |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- Qwen3ForCausalLM
- Parameters
- 7.6 B
- Tensor type
- BF16
- Context length
- 40,960
- Vocabulary
- 151,665
- Layers / heads
- 36 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2025-06-03
- Base model
- Qwen3-8B-Base
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any feature-extraction model