NVIDIA H200 SXM 141GB meets the minimum VRAM requirement for Q4 inference of google/embeddinggemma-300m. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA H200 SXM 141GB can run google/embeddinggemma-300m with Q4 quantization. At approximately 849 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 140GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 1GB | 141GB | 849.23 tok/s | ✅ Fits comfortably |
| Q8 | 1GB | 141GB | 597.05 tok/s | ✅ Fits comfortably |
| FP16 | 1GB | 141GB | 293.70 tok/s | ✅ Fits comfortably |