Qwen3-Embedding-8B
by Qwen
7.6B params · feature-extraction · 607 likes · 1.8M downloads
Qwen3-Embedding-8B is a 7.6B parameter model. At Q4 quantization it requires 4GB of VRAM. It runs comfortably on GeForce RTX 4090 (173 tok/s), GeForce RTX 5090 (260 tok/s), M4 Max 128GB (63 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Scaleway |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 173 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 260 tok/s | comfortable |
| M4 Max 128GB | 128GB | 63 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 31 tok/s | comfortable |
| M4 Pro 24GB | 24GB | 31 tok/s | comfortable |
| A100 PCIe 80 GB | 80GB | 317 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 639 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 153 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 126 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 123 tok/s | comfortable |