AMD Instinct MI300X meets the minimum VRAM requirement for Q4 inference of EssentialAI/rnj-1. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Instinct MI300X can run EssentialAI/rnj-1 with Q4 quantization. At approximately 565 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 187GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 5GB | 192GB | 565.11 tok/s | ✅ Fits comfortably |
| Q8 | 10GB | 192GB | 418.60 tok/s | ✅ Fits comfortably |
| FP16 | 19GB | 192GB | 212.02 tok/s | ✅ Fits comfortably |