AI Mo Kimina Prover 72B speed on NVIDIA A6000 and quantization-level VRAM fit.
NVIDIA A6000 meets the minimum VRAM requirement for Q4 inference of AI Mo Kimina Prover 72B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
NVIDIA A6000 can run AI Mo Kimina Prover 72B with Q4 quantization. At approximately 26 tokens/second, you can expect Moderate speed - useful for batch processing.
You have 11GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 37GB | 48GB | 26.48 tok/s | ✅ Fits comfortably |
| Q8 | 73GB | 48GB | 18.53 tok/s | ❌ Not recommended |
| FP16 | 146GB | 48GB | 10.06 tok/s | ❌ Not recommended |
Need a GPU with 37GB+ VRAM? These guides match your requirements.
Check current pricing links for NVIDIA A6000 and similar cards.
Open NVIDIA A6000 buy links →Use workload-focused recommendations before committing to a purchase.
Browse best GPU guides →Compare complete systems if you want ready-to-run hardware.
Compare prebuilt systems →Rent cloud GPUs by the hour — no upfront hardware cost.
NVIDIA A6000 can run AI Mo Kimina Prover 72B at Q4 with an estimated 26 tok/s.
Q4 inference is estimated to need about 37GB VRAM on this page, while NVIDIA A6000 has 48GB available.
If you need more speed or context headroom, compare alternative GPUs below and check higher-tier VRAM options.