NVIDIA H100 SXM5 80GB meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen3-Embedding-0.6B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA H100 SXM5 80GB can run Qwen/Qwen3-Embedding-0.6B with Q4 quantization. At approximately 484 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 77GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 3GB | 80GB | 484.22 tok/s | ✅ Fits comfortably |
| Q8 | 6GB | 80GB | 372.15 tok/s | ✅ Fits comfortably |
| FP16 | 13GB | 80GB | 189.92 tok/s | ✅ Fits comfortably |