Can it run?
Runs well
Using Q4_K_M in vLLM
Fit status
Runs well
Decode
65.6 tok/s
TTFT
2952 ms
Safe context
4K
Memory
67.2 GB / 96.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 73.8 tok/s | 3817 ms | 4K |
| Chat | B | Runs well | 73.8 tok/s | 1431 ms | 4K |
| Coding | B | Runs well | 65.6 tok/s | 2952 ms | 4K |
| RAG | B | Runs well | 73.8 tok/s | 4772 ms | 4K |
| Reasoning | B | Runs well | 73.8 tok/s | 3102 ms | 4K |
How Qwen 2.5 Math 72B (72B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 28.1 GB | Low | D36 |
Q3_K_S | 3 | 35.3 GB | Low | D37 |
NVFP4 | 4 |
ollama run qwen-2.5-math-72bhuggingface-cli download qwen-2.5-math-72b40.3 GB |
| Medium |
| D38 |
Q4_K_M | 4 | 43.9 GB | Medium | D39 |
Q5_K_M | 5 | 51.8 GB | High | C41 |
Q6_K | 6 | 59.0 GB | High | C43 |
Q8_0Best for your GPU | 8 | 77.0 GB | Very High | C44 |
F16 | 16 | 147.6 GB | Maximum | F0 |